AI Assistant Helpx

AI Assistant Helpx — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Contrastive Language-Image Pre-training

  Contrastive Language-Image Pre-training (CLIP) is a technique for training a pair of neural network models, one for image understanding and one for text understanding, using a contrastive objective. This method has enabled broad applications across multiple domains, including cross-modal retrieval, text-to-image generation, and aesthetic ranking. == Algorithm == The CLIP method trains a pair of models contrastively. One model takes in a piece of text as input and outputs a single vector representing its semantic content. The other model takes in an image and similarly outputs a single vector representing its visual content. The models are trained so that the vectors corresponding to semantically similar text-image pairs are close together in the shared vector space, while those corresponding to dissimilar pairs are far apart. To train a pair of CLIP models, one would start by preparing a large dataset of image-caption pairs. During training, the models are presented with batches of N {\displaystyle N} image-caption pairs. Let the outputs from the text and image models be respectively v 1 , . . . , v N , w 1 , . . . , w N {\displaystyle v_{1},...,v_{N},w_{1},...,w_{N}} . Two vectors are considered "similar" if their dot product is large. The loss incurred on this batch is the multi-class N-pair loss, which is a symmetric cross-entropy loss over similarity scores: − 1 N ∑ i ln ⁡ e v i ⋅ w i / T ∑ j e v i ⋅ w j / T − 1 N ∑ j ln ⁡ e v j ⋅ w j / T ∑ i e v i ⋅ w j / T {\displaystyle -{\frac {1}{N}}\sum _{i}\ln {\frac {e^{v_{i}\cdot w_{i}/T}}{\sum _{j}e^{v_{i}\cdot w_{j}/T}}}-{\frac {1}{N}}\sum _{j}\ln {\frac {e^{v_{j}\cdot w_{j}/T}}{\sum _{i}e^{v_{i}\cdot w_{j}/T}}}} In essence, this loss function encourages the dot product between matching image and text vectors ( v i ⋅ w i {\displaystyle v_{i}\cdot w_{i}} ) to be high, while discouraging high dot products between non-matching pairs. The parameter T > 0 {\displaystyle T>0} is the temperature, which is parameterized in the original CLIP model as T = e − τ {\displaystyle T=e^{-\tau }} where τ ∈ R {\displaystyle \tau \in \mathbb {R} } is a learned parameter. Other loss functions are possible. For example, Sigmoid CLIP (SigLIP) proposes the following loss function: L = 1 N ∑ i , j ∈ 1 : N f ( ( 2 δ i , j − 1 ) ( e τ w i ⋅ v j + b ) ) {\displaystyle L={\frac {1}{N}}\sum _{i,j\in 1:N}f((2\delta _{i,j}-1)(e^{\tau }w_{i}\cdot v_{j}+b))} where f ( x ) = ln ⁡ ( 1 + e − x ) {\displaystyle f(x)=\ln(1+e^{-x})} is the negative log sigmoid loss, and the Dirac delta symbol δ i , j {\displaystyle \delta _{i,j}} is 1 if i = j {\displaystyle i=j} else 0. == CLIP models == While the original model was developed by OpenAI, subsequent models have been trained by other organizations as well. === Image model === The image encoding models used in CLIP are typically vision transformers (ViT). The naming convention for these models often reflects the specific ViT architecture used. For instance, "ViT-L/14" means a "vision transformer large" (compared to other models in the same series) with a patch size of 14, meaning that the image is divided into 14-by-14 pixel patches before being processed by the transformer. The size indicator ranges from B, L, H, G (base, large, huge, giant), in that order. Other than ViT, the image model is typically a convolutional neural network, such as ResNet (in the original series by OpenAI), or ConvNeXt (in the OpenCLIP model series by LAION). Since the output vectors of the image model and the text model must have exactly the same length, both the image model and the text model have fixed-length vector outputs, which in the original report is called "embedding dimension". For example, in the original OpenAI model, the ResNet models have embedding dimensions ranging from 512 to 1024, and for the ViTs, from 512 to 768. Its implementation of ViT was the same as the original one, with one modification: after position embeddings are added to the initial patch embeddings, there is a LayerNorm. Its implementation of ResNet was the same as the original one, with 3 modifications: In the start of the CNN (the "stem"), they used three stacked 3x3 convolutions instead of a single 7x7 convolution, as suggested by. There is an average pooling of stride 2 at the start of each downsampling convolutional layer (they called it rect-2 blur pooling according to the terminology of ). This has the effect of blurring images before downsampling, for antialiasing. The final convolutional layer is followed by a multiheaded attention pooling. ALIGN a model with similar capabilities, trained by researchers from Google used EfficientNet, a kind of convolutional neural network. === Text model === The text encoding models used in CLIP are typically Transformers. In the original OpenAI report, they reported using a Transformer (63M-parameter, 12-layer, 512-wide, 8 attention heads) with lower-cased byte pair encoding (BPE) with 49152 vocabulary size. Context length was capped at 76 for efficiency. Like GPT, it was decoder-only, with only causally-masked self-attention. Its architecture is the same as GPT-2. Like BERT, the text sequence is bracketed by two special tokens [SOS] and [EOS] ("start of sequence" and "end of sequence"). Take the activations of the highest layer of the transformer on the [EOS], apply LayerNorm, then a final linear map. This is the text encoding of the input sequence. The final linear map has output dimension equal to the embedding dimension of whatever image encoder it is paired with. These models all had context length 77 and vocabulary size 49408. ALIGN used BERT of various sizes. == Dataset == === WebImageText === The CLIP models released by OpenAI were trained on a dataset called "WebImageText" (WIT) containing 400 million pairs of images and their corresponding captions scraped from the internet. The total number of words in this dataset is similar in scale to the WebText dataset used for training GPT-2, which contains about 40 gigabytes of text data. The dataset contains 500,000 text-queries, with up to 20,000 (image, text) pairs per query. The text-queries were generated by starting with all words occurring at least 100 times in English Wikipedia, then extended by bigrams with high mutual information, names of all Wikipedia articles above a certain search volume, and WordNet synsets. The dataset is private and has not been released to the public, and there is no further information on it. ==== Data preprocessing ==== For the CLIP image models, the input images are preprocessed by first dividing each of the R, G, B values of an image by the maximum possible value, so that these values fall between 0 and 1, then subtracting by [0.48145466, 0.4578275, 0.40821073], and dividing by [0.26862954, 0.26130258, 0.27577711]. The rationale was that these are the mean and standard deviations of the images in the WebImageText dataset, so this preprocessing step roughly whitens the image tensor. These numbers slightly differ from the standard preprocessing for ImageNet, which uses [0.485, 0.456, 0.406] and [0.229, 0.224, 0.225]. If the input image does not have the same resolution as the native resolution (224×224 for all except ViT-L/14@336px, which has 336×336 resolution), then the input image is first scaled by bicubic interpolation, so that its shorter side is the same as the native resolution, then the central square of the image is cropped out. === Others === ALIGN used over one billion image-text pairs, obtained by extracting images and their alt-tags from online crawling. The method was described as similar to how the Conceptual Captions dataset was constructed, but instead of complex filtering, they only applied a frequency-based filtering. Later models trained by other organizations had published datasets. For example, LAION trained OpenCLIP with published datasets LAION-400M, LAION-2B, and DataComp-1B. == Training == In the original OpenAI CLIP report, they reported training 5 ResNet and 3 ViT (ViT-B/32, ViT-B/16, ViT-L/14). Each was trained for 32 epochs. The largest ResNet model took 18 days to train on 592 V100 GPUs. The largest ViT model took 12 days on 256 V100 GPUs. All ViT models were trained on 224×224 image resolution. The ViT-L/14 was then boosted to 336×336 resolution by FixRes, resulting in a model. They found this was the best-performing model. In the OpenCLIP series, the ViT-L/14 model was trained on 384 A100 GPUs on the LAION-2B dataset, for 160 epochs for a total of 32B samples seen. == Applications == === Cross-modal retrieval === CLIP's cross-modal retrieval enables the alignment of visual and textual data in a shared latent space, allowing users to retrieve images based on text descriptions and vice versa, without the need for explicit image annotations. In text-to-image retrieval, users input descriptive text, and CLIP retrieves images with matching embeddings. In image-to-text retrieval, images are used to find related text content. CLIP’s ability to connect vis

  Read more →
• 

  Apprenticeship learning

  In artificial intelligence, apprenticeship learning (or learning from demonstration or imitation learning) is the process of learning by observing an expert. It can be viewed as a form of supervised learning, where the training dataset consists of task executions by a demonstration teacher. == Mapping function approach == Mapping methods try to mimic the expert by forming a direct mapping either from states to actions, or from states to reward values. For example, in 2002 researchers used such an approach to teach an AIBO robot basic soccer skills. === Inverse reinforcement learning approach === Inverse reinforcement learning (IRL) is the process of deriving a reward function from observed behavior. While ordinary "reinforcement learning" involves using rewards and punishments to learn behavior, in IRL the direction is reversed, and a robot observes a person's behavior to figure out what goal that behavior seems to be trying to achieve. The IRL problem can be defined as: Given 1) measurements of an agent's behaviour over time, in a variety of circumstances; 2) measurements of the sensory inputs to that agent; 3) a model of the physical environment (including the agent's body): Determine the reward function that the agent is optimizing. IRL researcher Stuart J. Russell proposes that IRL might be used to observe humans and attempt to codify their complex "ethical values", in an effort to create "ethical robots" that might someday know "not to cook your cat" without needing to be explicitly told. The scenario can be modeled as a "cooperative inverse reinforcement learning game", where a "person" player and a "robot" player cooperate to secure the person's implicit goals, despite these goals not being explicitly known by either the person nor the robot. In 2017, OpenAI and DeepMind applied deep learning to the cooperative inverse reinforcement learning in simple domains such as Atari games and straightforward robot tasks such as backflips. The human role was limited to answering queries from the robot as to which of two different actions were preferred. The researchers found evidence that the techniques may be economically scalable to modern systems. Apprenticeship via inverse reinforcement learning (AIRP) was developed by in 2004 Pieter Abbeel, Professor in Berkeley's EECS department, and Andrew Ng, Associate Professor in Stanford University's Computer Science Department. AIRP deals with "Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we want to learn to perform". AIRP has been used to model reward functions of highly dynamic scenarios where there is no obvious reward function intuitively. Take the task of driving for example, there are many different objectives working simultaneously - such as maintaining safe following distance, a good speed, not changing lanes too often, etc. This task, may seem easy at first glance, but a trivial reward function may not converge to the policy wanted. One domain where AIRP has been used extensively is helicopter control. While simple trajectories can be intuitively derived, complicated tasks like aerobatics for shows has been successful. These include aerobatic maneuvers like - in-place flips, in-place rolls, loops, hurricanes and even auto-rotation landings. This work was developed by Pieter Abbeel, Adam Coates, and Andrew Ng - "Autonomous Helicopter Aerobatics through Apprenticeship Learning" === System model approach === System models try to mimic the expert by modeling world dynamics. == Plan approach == The system learns rules to associate preconditions and postconditions with each action. In one 1994 demonstration, a humanoid learns a generalized plan from only two demonstrations of a repetitive ball collection task. == Example == Learning from demonstration is often explained from a perspective that the working Robot-control-system is available and the human-demonstrator is using it. And indeed, if the software works, the Human operator takes the robot-arm, makes a move with it, and the robot will reproduce the action later. For example, he teaches the robot-arm how to put a cup under a coffeemaker and press the start-button. In the replay phase, the robot is imitating this behavior 1:1. But that is not how the system works internally; it is only what the audience can observe. In reality, Learning from demonstration is much more complex. One of the first works on learning by robot apprentices (anthropomorphic robots learning by imitation) was Adrian Stoica's PhD thesis in 1995. In 1997, robotics expert Stefan Schaal was working on the Sarcos robot-arm. The goal was simple: solve the pendulum swingup task. The robot itself can execute a movement, and as a result, the pendulum is moving. The problem is, that it is unclear what actions will result into which movement. It is an Optimal control-problem which can be described with mathematical formulas but is hard to solve. The idea from Schaal was, not to use a Brute-force solver but record the movements of a human-demonstration. The angle of the pendulum is logged over three seconds at the y-axis. This results into a diagram which produces a pattern. In computer animation, the principle is called spline animation. That means, on the x-axis the time is given, for example 0.5 seconds, 1.0 seconds, 1.5 seconds, while on the y-axis is the variable given. In most cases it's the position of an object. In the inverted pendulum it is the angle. The overall task consists of two parts: recording the angle over time and reproducing the recorded motion. The reproducing step is surprisingly simple. As an input we know, in which time step which angle the pendulum must have. Bringing the system to a state is called “Tracking control” or PID control. That means, we have a trajectory over time, and must find control actions to map the system to this trajectory. Other authors call the principle “steering behavior”, because the aim is to bring a robot to a given line.

  Read more →
• 

  Machine learning in video games

  Artificial intelligence and machine learning techniques are used in video games for a wide variety of applications such as non-player character (NPC) control, procedural content generation (PCG) and deep learning-based content generation. Machine learning is a subset of artificial intelligence that uses historical data to build predictive and analytical models. This is in sharp contrast to traditional methods of artificial intelligence such as search trees and expert systems. Information on machine learning techniques in the field of games is mostly known to public through research projects as most gaming companies choose not to publish specific information about their intellectual property. The most publicly known application of machine learning in games is likely the use of deep learning agents that compete with professional human players in complex strategy games. There has been a significant application of machine learning on games such as Atari/ALE, Doom, Minecraft, StarCraft, and car racing. Other games that did not originally exists as video games, such as chess and Go have also been affected by the machine learning. == Overview of relevant machine learning techniques == === Deep learning === Deep learning is a subset of machine learning which focuses heavily on the use of artificial neural networks (ANN) that learn to solve complex tasks. Deep learning uses multiple layers of ANN and other techniques to progressively extract information from an input. Due to this complex layered approach, deep learning models often require powerful machines to train and run on. ==== Convolutional neural networks ==== Convolutional neural networks (CNN) are specialized ANNs that are often used to analyze image data. These types of networks are able to learn translation invariant patterns, which are patterns that are not dependent on location. CNNs are able to learn these patterns in a hierarchy, meaning that earlier convolutional layers will learn smaller local patterns while later layers will learn larger patterns based on the previous patterns. A CNN's ability to learn visual data has made it a commonly used tool for deep learning in games. === Recurrent neural network === Recurrent neural networks are a type of ANN that are designed to process sequences of data in order, one part at a time rather than all at once. An RNN runs over each part of a sequence, using the current part of the sequence along with memory of previous parts of the current sequence to produce an output. These types of ANN are highly effective at tasks such as speech recognition and other problems that depend heavily on temporal order. There are several types of RNNs with different internal configurations; the basic implementation suffers from a lack of long term memory due to the vanishing gradient problem, thus it is rarely used over newer implementations. ==== Long short-term memory ==== A long short-term memory (LSTM) network is a specific implementation of a RNN that is designed to deal with the vanishing gradient problem seen in simple RNNs, which would lead to them gradually "forgetting" about previous parts of an inputted sequence when calculating the output of a current part. LSTMs solve this problem with the addition of an elaborate system that uses an additional input/output to keep track of long term data. LSTMs have achieved very strong results across various fields, and were used by several monumental deep learning agents in games. === Reinforcement learning === Reinforcement learning is the process of training an agent using rewards and/or punishments. The way an agent is rewarded or punished depends heavily on the problem; such as giving an agent a positive reward for winning a game or a negative one for losing. Reinforcement learning is used heavily in the field of machine learning and can be seen in methods such as Q-learning, policy search, Deep Q-networks and others. It has seen strong performance in both the field of games and robotics. === Neuroevolution === Neuroevolution involves the use of both neural networks and evolutionary algorithms. Instead of using gradient descent like most neural networks, neuroevolution models make use of evolutionary algorithms to update neurons in the network. Researchers claim that this process is less likely to get stuck in a local minimum and is potentially faster than state of the art deep learning techniques. == Deep learning agents == Machine learning agents have been used to take the place of a human player rather than function as NPCs, which are deliberately added into video games as part of designed gameplay. Deep learning agents have achieved impressive results when used in competition with both humans and other artificial intelligence agents. === Chess === Chess is a turn-based strategy game that is considered a difficult AI problem due to the computational complexity of its board space. Similar strategy games are often solved with some form of a Minimax Tree Search. These types of AI agents have been known to beat professional human players, such as the historic 1997 Deep Blue versus Garry Kasparov match. Since then, machine learning agents have shown ever greater success than previous AI agents. === Go === Go is another turn-based strategy game which is considered an even more difficult AI problem than chess. The state space of is Go is around 10^170 possible board states compared to the 10^120 board states for Chess. Prior to recent deep learning models, AI Go agents were only able to play at the level of a human amateur. ==== AlphaGo ==== Google's 2015 AlphaGo was the first AI agent to beat a professional Go player. AlphaGo used a deep learning model to train the weights of a Monte Carlo tree search (MCTS). The deep learning model consisted of 2 ANN, a policy network to predict the probabilities of potential moves by opponents, and a value network to predict the win chance of a given state. The deep learning model allows the agent to explore potential game states more efficiently than a vanilla MCTS. The network were initially trained on games of humans players and then were further trained by games against itself. ==== AlphaGo Zero ==== AlphaGo Zero, another implementation of AlphaGo, was able to train entirely by playing against itself. It was able to quickly train up to the capabilities of the previous agent. === StarCraft series === StarCraft and its sequel StarCraft II are real-time strategy (RTS) video games that have become popular environments for AI research. Blizzard and DeepMind have worked together to release a public StarCraft 2 environment for AI research to be done on. Various deep learning methods have been tested on both games, though most agents usually have trouble outperforming the default AI with cheats enabled or skilled players of the game. ==== Alphastar ==== Alphastar was the first AI agent to beat professional StarCraft 2 players without any in-game advantages. The deep learning network of the agent initially received input from a simplified zoomed out version of the gamestate, but was later updated to play using a camera like other human players. The developers have not publicly released the code or architecture of their model, but have listed several state of the art machine learning techniques such as relational deep reinforcement learning, long short-term memory, auto-regressive policy heads, pointer networks, and centralized value baseline. Alphastar was initially trained with supervised learning, it watched replays of many human games in order to learn basic strategies. It then trained against different versions of itself and was improved through reinforcement learning. The final version was hugely successful, but only trained to play on a specific map in a protoss mirror matchup. === Dota 2 === Dota 2 is a multiplayer online battle arena (MOBA) game. Like other complex games, traditional AI agents have not been able to compete on the same level as professional human player. The only widely published information on AI agents attempted on Dota 2 is OpenAI's deep learning Five agent. ==== OpenAI Five ==== OpenAI Five utilized separate long short-term memory networks to learn each hero. It trained using a reinforcement learning technique known as Proximal Policy Learning running on a system containing 256 GPUs and 128,000 CPU cores. Five trained for months, accumulating 180 years of game experience each day, before facing off with professional players. It was eventually able to beat the 2018 Dota 2 esports champion team in a 2019 series of games. === Planetary Annihilation === Planetary Annihilation is a real-time strategy game which focuses on massive scale war. The developers use ANNs in their default AI agent. === Supreme Commander 2 === Supreme Commander 2 is a real-time strategy (RTS) video game. The game uses Multilayer Perceptrons (MLPs) to control a platoon’s reaction to encountered enemy units. Total of four MLPs are used, one for each platoon type: land, naval

  Read more →
• 

  Mountain car problem

  Mountain Car, a standard testing domain in Reinforcement learning, is a problem in which an under-powered car must drive up a steep hill. Since gravity is stronger than the car's engine, even at full throttle, the car cannot simply accelerate up the steep slope. The car is situated in a valley and must learn to leverage potential energy by driving up the opposite hill before the car is able to make it to the goal at the top of the rightmost hill. The domain has been used as a test bed in various reinforcement learning papers. == Introduction == The mountain car problem, although fairly simple, is commonly applied because it requires a reinforcement learning agent to learn on two continuous variables: position and velocity. For any given state (position and velocity) of the car, the agent is given the possibility of driving left, driving right, or not using the engine at all. In the standard version of the problem, the agent receives a negative reward at every time step when the goal is not reached; the agent has no information about the goal until an initial success. == History == The mountain car problem appeared first in Andrew Moore's PhD thesis (1990). It was later more strictly defined in Singh and Sutton's reinforcement learning paper with eligibility traces. The problem became more widely studied when Sutton and Barto added it to their book Reinforcement Learning: An Introduction (1998). Throughout the years many versions of the problem have been used, such as those which modify the reward function, termination condition, and the start state. == Techniques used to solve mountain car == Q-learning and similar techniques for mapping discrete states to discrete actions need to be extended to be able to deal with the continuous state space of the problem. Approaches often fall into one of two categories, state space discretization or function approximation. === Discretization === In this approach, two continuous state variables are pushed into discrete states by bucketing each continuous variable into multiple discrete states. This approach works with properly tuned parameters but a disadvantage is information gathered from one state is not used to evaluate another state. Tile coding can be used to improve discretization and involves continuous variables mapping into sets of buckets offset from one another. Each step of training has a wider impact on the value function approximation because when the offset grids are summed, the information is diffused. === Function approximation === Function approximation is another way to solve the mountain car. By choosing a set of basis functions beforehand, or by generating them as the car drives, the agent can approximate the value function at each state. Unlike the step-wise version of the value function created with discretization, function approximation can more cleanly estimate the true smooth function of the mountain car domain. === Eligibility traces === One aspect of the problem involves the delay of actual reward. The agent is not able to learn about the goal until a successful completion. Given a naive approach for each trial the car can only backup the reward of the goal slightly. This is a problem for naive discretization because each discrete state will only be backed up once, taking a larger number of episodes to learn the problem. This problem can be alleviated via the mechanism of eligibility traces, which will automatically backup the reward given to states before, dramatically increasing the speed of learning. Eligibility traces can be viewed as a bridge from temporal difference learning methods to Monte Carlo methods. == Technical details == The mountain car problem has undergone many iterations. This section focuses on the standard well-defined version from Sutton (2008). === State variables === Two-dimensional continuous state space. V e l o c i t y = ( − 0.07 , 0.07 ) {\displaystyle Velocity=(-0.07,0.07)} P o s i t i o n = ( − 1.2 , 0.6 ) {\displaystyle Position=(-1.2,0.6)} === Actions === One-dimensional discrete action space. m o t o r = ( l e f t , n e u t r a l , r i g h t ) {\displaystyle motor=(left,neutral,right)} === Reward === For every time step: r e w a r d = − 1 {\displaystyle reward=-1} === Update function === For every time step: A c t i o n = [ − 1 , 0 , 1 ] {\displaystyle Action=[-1,0,1]} V e l o c i t y = V e l o c i t y + ( A c t i o n ) ∗ 0.001 + cos ⁡ ( 3 ∗ P o s i t i o n ) ∗ ( − 0.0025 ) {\displaystyle Velocity=Velocity+(Action)0.001+\cos(3Position)(-0.0025)} P o s i t i o n = P o s i t i o n + V e l o c i t y {\displaystyle Position=Position+Velocity} === Starting condition === Optionally, many implementations include randomness in both parameters to show better generalized learning. P o s i t i o n = − 0.5 {\displaystyle Position=-0.5} V e l o c i t y = 0.0 {\displaystyle Velocity=0.0} === Termination condition === End the simulation when: P o s i t i o n ≥ 0.6 {\displaystyle Position\geq 0.6} == Variations == There are many versions of the mountain car which deviate in different ways from the standard model. Variables that vary include but are not limited to changing the constants (gravity and steepness) of the problem so specific tuning for specific policies become irrelevant and altering the reward function to affect the agent's ability to learn in a different manner. An example is changing the reward to be equal to the distance from the goal, or changing the reward to zero everywhere and one at the goal. Additionally, a 3D mountain car can be used, with a 4D continuous state space.

  Read more →
• 

  ReactiveX

  ReactiveX (Rx, also known as Reactive Extensions) is a software library originally created by Microsoft that allows imperative programming languages to operate on sequences of data regardless of whether the data is synchronous or asynchronous. It provides a set of sequence operators that operate on each item in the sequence. It is an implementation of reactive programming and provides a blueprint for the tools to be implemented in multiple programming languages. == Overview == ReactiveX is an API for asynchronous programming with observable streams. Asynchronous programming allows programmers to call functions and then have the functions "callback" when they are done, usually by giving the function the address of another function to execute when it is done. Programs designed in this way often avoid the overhead of having many threads constantly starting and stopping. Observable streams (i.e. streams that can be observed) in the context of Reactive Extensions are like event emitters that emit three events: next, error, and complete. An observable emits next events until it either emits an error event or a complete event. However, at that point it will not emit any more events, unless it is subscribed to again. The examples below use the RxJS implementation of Reactive Extensions for the JavaScript programming language. === Motivation === For sequences of data, it combines the advantages of iterators with the flexibility of event-based asynchronous programming. It also works as a simple promise, eliminating the pyramid of doom that results from multiple layers of callbacks. === Observables and observers === ReactiveX is a combination of ideas from the observer and the iterator patterns and from functional programming. An observer subscribes to an observable sequence. The sequence then sends the items to the observer one at a time, usually by calling the provided callback function. The observer handles each one before processing the next one. If many events come in asynchronously, they must be stored in a queue or dropped. In ReactiveX, an observer will never be called with an item out of order or (in a multi-threaded context) called before the callback has returned for the previous item. Asynchronous calls remain asynchronous and may be handled by returning an observable. It is similar to the iterators pattern in that if a fatal error occurs, it notifies the observer separately (by calling a second function). When all the items have been sent, it completes (and notifies the observer by calling a third function). The Reactive Extensions API also borrows many of its operators from iterator operators in other programming languages. Reactive Extensions is different from functional reactive programming as the Introduction to Reactive Extensions explains: It is sometimes called "functional reactive programming" but this is a misnomer. ReactiveX may be functional, and it may be reactive, but "functional reactive programming" is a different animal. One main point of difference is that functional reactive programming operates on values that change continuously over time, while ReactiveX operates on discrete values that are emitted over time. (See Conal Elliott's work for more-precise information on functional reactive programming.) === Reactive operators === An operator is a function that takes one observable (the source) as its first argument and returns another observable (the destination, or outer observable). Then for every item that the source observable emits, it will apply a function to that item, and then emit it on the destination Observable. It can even emit another Observable on the destination observable. This is called an inner observable. An operator that emits inner observables can be followed by another operator that in some way combines the items emitted by all the inner observables and emits the item on its outer observable. Examples include: switchAll – subscribes to each new inner observable as soon as it is emitted and unsubscribes from the previous one. mergeAll – subscribes to all inner observables as they are emitted and outputs their values in whatever order it receives them. concatAll – subscribes to each inner observable in order and waits for it to complete before subscribing to the next observable. Operators can be chained together to create complex data flows that filter events based on certain criteria. Multiple operators can be applied to the same observable. Some of the operators that can be used in Reactive Extensions may be familiar to programmers who use functional programming language, such as map, reduce, group, and zip. There are many other operators available in Reactive Extensions, though the operators available in a particular implementation for a programming language may vary. ==== Reactive operator examples ==== Here is an example of using the map and reduce operators. We create an observable from a list of numbers. The map operator will then multiply each number by two and return an observable. The reduce operator will then sum up all the numbers provided to it (the value of 0 is the starting point). Calling subscribe will register an observer that will observe the values from the observable produced by the chain of operators. With the subscribe method, we are able to pass in an error-handling function, called whenever an error is emitted in the observable, and a completion function when the observable has finished emitting items. ==== Usage in stream-oriented programming ==== Certain RxJS primitives such as BehaviorSubject make it possible to create pure stateful streams to track application state of arbitrary complexity in simple terms. The button below will feed an event to the stream, which in turn will re-emit the next natural number every time, back into the tag that follows and displays the count of clicks detected. Libraries such as Rimmel.js, designed around RxJS Observables, enable integration between reactive streams and the HTML DOM: == History == Reactive Extensions was created by the Cloud Programmability Team at Microsoft around 2011, as a byproduct of a larger effort called Volta. It was originally intended to provide an abstraction for events across different tiers in an application to support tier splitting in Volta. The project's logo represents an electric eel, which is a reference to Volta. The extensions suffix in the name is a reference to the Parallel Extensions technology which was invented around the same time; the two are considered complementary. The initial implementation of Rx was for .NET Framework and was released on June 21, 2011. Later, the team started the implementation of Rx for other platforms, including JavaScript and C++. The technology was released as open source in late 2012, initially on CodePlex. Later, the code moved to GitHub and has been ported to several other languages, including Go, Java, Kotlin, PHP and Rust.

  Read more →
• 

  AI-complete

  In the field of artificial intelligence (AI), tasks that are hypothesized to require artificial general intelligence to solve are informally known as AI-complete or AI-hard. Calling a problem AI-complete reflects the belief that it cannot be solved by a simple specific algorithm. Prior to 2013, problems supposed to be AI-complete included computer vision, natural language understanding, and dealing with unexpected circumstances while solving any real-world problem. AI-complete tasks were notably considered useful for distinguishing humans from automated agents, as CAPTCHAs aim to do. == History == The term was coined by Fanya Montalvo by analogy with NP-complete and NP-hard in complexity theory, which formally describes the most famous class of difficult problems. Early uses of the term are in Erik Mueller's 1987 PhD dissertation and in Eric Raymond's 1991 Jargon File. Expert systems, that were popular in the 1980s, were able to solve very simple and/or restricted versions of AI-complete problems, but never in their full generality. When AI researchers attempted to "scale up" their systems to handle more complicated, real-world situations, the programs tended to become excessively brittle without commonsense knowledge or a rudimentary understanding of the situation: they would fail as unexpected circumstances outside of its original problem context would begin to appear. When human beings are dealing with new situations in the world, they are helped by their awareness of the general context: they know what the things around them are, why they are there, what they are likely to do and so on. They can recognize unusual situations and adjust accordingly. Expert systems lacked this adaptability and were brittle when facing new situations. DeepMind published a work in May 2022 in which they trained a single model to do several things at the same time. The model, named Gato, can "play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens." Similarly, some tasks once considered to be AI-complete, like machine translation, are among the capabilities of large language models. == AI-complete problems == AI-complete problems have been hypothesized to include: AI peer review (composite natural language understanding, automated reasoning, automated theorem proving, formalized logic expert system) Bongard problems Computer vision (and subproblems such as object recognition) Natural language understanding (and subproblems such as text mining, machine translation, and word-sense disambiguation) Autonomous driving Dealing with unexpected circumstances while solving any real world problem, whether navigation, planning, or even the kind of reasoning done by expert systems. == Formalization == Computational complexity theory deals with the relative computational difficulty of computable functions. By definition, it does not cover problems whose solution is unknown or has not been characterized formally. Since many AI problems have no formalization yet, conventional complexity theory does not enable a formal definition of AI-completeness. == Research == Roman Yampolskiy suggests that a problem C {\displaystyle C} is AI-Complete if it has two properties: It is in the set of AI problems (Human Oracle-solvable). Any AI problem can be converted into C {\displaystyle C} by some polynomial time algorithm. On the other hand, a problem H {\displaystyle H} is AI-Hard if and only if there is an AI-Complete problem C {\displaystyle C} that is polynomial time Turing-reducible to H {\displaystyle H} . This also gives as a consequence the existence of AI-Easy problems, that are solvable in polynomial time by a deterministic Turing machine with an oracle for some problem. Yampolskiy has also hypothesized that the Turing Test is a defining feature of AI-completeness. Groppe and Jain classify problems which require artificial general intelligence to reach human-level machine performance as AI-complete, while only restricted versions of AI-complete problems can be solved by the current AI systems. For Šekrst, getting a polynomial solution to AI-complete problems would not necessarily be equal to solving the issue of artificial general intelligence, while emphasizing the lack of computational complexity research being the limiting factor towards achieving artificial general intelligence. For Kwee-Bintoro and Velez, solving AI-complete problems would have strong repercussions on society.

  Read more →
• 

  Learning to rank

  Learning to rank (LTR) or machine-learned ranking (MLR) is the application of machine learning, often supervised, semi-supervised or reinforcement learning, in the construction of ranking models for information retrieval and recommender systems. Training data may, for example, consist of lists of items with some partial order specified between items in each list. This order is typically induced by giving a numerical or ordinal score or a binary judgment (e.g. "relevant" or "not relevant") for each item. The goal of constructing the ranking model is to rank new, unseen lists in a similar way to rankings in the training data. == Applications == === In information retrieval === Ranking is a central part of many information retrieval problems, such as document retrieval, collaborative filtering, sentiment analysis, and online advertising. A possible architecture of a machine-learned search engine is shown in the accompanying figure. Training data consists of queries and documents matching them together with the relevance degree of each match. It may be prepared manually by human assessors (or raters, as Google calls them), who check results for some queries and determine relevance of each result. It is not feasible to check the relevance of all documents, and so typically a technique called pooling is used — only the top few documents, retrieved by some existing ranking models are checked. This technique may introduce selection bias. Alternatively, training data may be derived automatically by analyzing clickthrough logs (i.e. search results which got clicks from users), query chains, or such search engines' features as Google's (since-replaced) SearchWiki. Clickthrough logs can be biased by the tendency of users to click on the top search results on the assumption that they are already well-ranked. Training data is used by a learning algorithm to produce a ranking model which computes the relevance of documents for actual queries. Typically, users expect a search query to complete in a short time (such as a few hundred milliseconds for web search), which makes it impossible to evaluate a complex ranking model on each document in the corpus, and so a two-phase scheme is used. First, a small number of potentially relevant documents are identified using simpler retrieval models which permit fast query evaluation, such as the vector space model, Boolean model, weighted AND, or BM25. This phase is called top- k {\displaystyle k} document retrieval and many heuristics were proposed in the literature to accelerate it, such as using a document's static quality score and tiered indexes. In the second phase, a more accurate but computationally expensive machine-learned model is used to re-rank these documents. === In other areas === Learning to rank algorithms have been applied in areas other than information retrieval: In machine translation for ranking a set of hypothesized translations; In computational biology for ranking candidate 3-D structures in protein structure prediction problems; In recommender systems for identifying a ranked list of related news articles to recommend to a user after he or she has read a current news article. == Feature vectors == For the convenience of MLR algorithms, query-document pairs are usually represented by numerical vectors, which are called feature vectors. Such an approach is sometimes called bag of features and is analogous to the bag of words model and vector space model used in information retrieval for representation of documents. Components of such vectors are called features, factors or ranking signals. They may be divided into three groups (features from document retrieval are shown as examples): Query-independent or static features — those features, which depend only on the document, but not on the query. For example, PageRank or document's length. Such features can be precomputed in off-line mode during indexing. They may be used to compute document's static quality score (or static rank), which is often used to speed up search query evaluation. Query-dependent or dynamic features — those features, which depend both on the contents of the document and the query, such as TF-IDF score or other non-machine-learned ranking functions. Query-level features or query features, which depend only on the query. For example, the number of words in a query. Some examples of features, which were used in the well-known LETOR dataset: TF, TF-IDF, BM25, and language modeling scores of document's zones (title, body, anchors text, URL) for a given query; Lengths and IDF sums of document's zones; Document's PageRank, HITS ranks and their variants. Selecting and designing good features is an important area in machine learning, which is called feature engineering. == Evaluation measures == There are several measures (metrics) which are commonly used to judge how well an algorithm is doing on training data and to compare the performance of different MLR algorithms. Often a learning-to-rank problem is reformulated as an optimization problem with respect to one of these metrics. Examples of ranking quality measures: Mean average precision (MAP); DCG and NDCG; Precision@n, NDCG@n, where "@n" denotes that the metrics are evaluated only on top n documents; Mean reciprocal rank; Kendall's tau; Spearman's rho. DCG and its normalized variant NDCG are usually preferred in academic research when multiple levels of relevance are used. Other metrics such as MAP, MRR and precision, are defined only for binary judgments. Recently, there have been proposed several new evaluation metrics which claim to model user's satisfaction with search results better than the DCG metric: Expected reciprocal rank (ERR); Yandex's pfound. Both of these metrics are based on the assumption that the user is more likely to stop looking at search results after examining a more relevant document, than after a less relevant document. == Approaches == Learning to Rank approaches are often categorized using one of three approaches: pointwise (where individual documents are ranked), pairwise (where pairs of documents are ranked into a relative order), and listwise (where an entire list of documents are ordered). Tie-Yan Liu of Microsoft Research Asia has analyzed existing algorithms for learning to rank problems in his book Learning to Rank for Information Retrieval. He categorized them into three groups by their input spaces, output spaces, hypothesis spaces (the core function of the model) and loss functions: the pointwise, pairwise, and listwise approach. In practice, listwise approaches often outperform pairwise approaches and pointwise approaches. This statement was further supported by a large scale experiment on the performance of different learning-to-rank methods on a large collection of benchmark data sets. In this section, without further notice, x {\displaystyle x} denotes an object to be evaluated, for example, a document or an image, f ( x ) {\displaystyle f(x)} denotes a single-value hypothesis, h ( ⋅ ) {\displaystyle h(\cdot )} denotes a bi-variate or multi-variate function and L ( ⋅ ) {\displaystyle L(\cdot )} denotes the loss function. === Pointwise approach === In this case, it is assumed that each query-document pair in the training data has a numerical or ordinal score. Then the learning-to-rank problem can be approximated by a regression problem — given a single query-document pair, predict its score. Formally speaking, the pointwise approach aims at learning a function f ( x ) {\displaystyle f(x)} predicting the real-value or ordinal score of a document x {\displaystyle x} using the loss function L ( f ; x j , y j ) {\displaystyle L(f;x_{j},y_{j})} . A number of existing supervised machine learning algorithms can be readily used for this purpose. Ordinal regression and classification algorithms can also be used in pointwise approach when they are used to predict the score of a single query-document pair, and it takes a small, finite number of values. === Pairwise approach === In this case, the learning-to-rank problem is approximated by a classification problem — learning a binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} that can tell which document is better in a given pair of documents. The classifier shall take two documents as its input and the goal is to minimize a loss function L ( h ; x u , x v , y u , v ) {\displaystyle L(h;x_{u},x_{v},y_{u,v})} . The loss function typically reflects the number and magnitude of inversions in the induced ranking. In many cases, the binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} is implemented with a scoring function f ( x ) {\displaystyle f(x)} . As an example, RankNet adapts a probability model and defines h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} as the estimated probability of the document x u {\displaystyle x_{u}} has higher quality than x v {\displaystyle x_{v}} : P u , v ( f ) = CDF ( f ( x u ) − f ( x v ) ) , {\displaystyle P_{u,v}(f)={\text{CDF}

  Read more →
• 

  Lazy learning

  (Not to be confused with the lazy learning regime, see Neural tangent kernel). In machine learning, lazy learning is a learning method in which generalization of the training data is, in theory, delayed until a query is made to the system, as opposed to eager learning, where the system tries to generalize the training data before receiving queries. The primary motivation for employing lazy learning, as in the K-nearest neighbors algorithm, used by online recommendation systems ("people who viewed/purchased/listened to this movie/item/tune also ...") is that the data set is continuously updated with new entries (e.g., new items for sale at Amazon, new movies to view at Netflix, new clips at YouTube, new music at Spotify or Pandora). Because of the continuous update, the "training data" would be rendered obsolete in a relatively short time especially in areas like books and movies, where new best-sellers or hit movies/music are published/released continuously. Therefore, one cannot really talk of a "training phase". Lazy classifiers are most useful for large, continuously changing datasets with few attributes that are commonly queried. Specifically, even if a large set of attributes exist - for example, books have a year of publication, author/s, publisher, title, edition, ISBN, selling price, etc. - recommendation queries rely on far fewer attributes - e.g., purchase or viewing co-occurrence data, and user ratings of items purchased/viewed. == Advantages == The main advantage gained in employing a lazy learning method is that the target function will be approximated locally, such as in the k-nearest neighbor algorithm. Because the target function is approximated locally for each query to the system, lazy learning systems can simultaneously solve multiple problems and deal successfully with changes in the problem domain. At the same time they can reuse a lot of theoretical and applied results from linear regression modelling (notably PRESS statistic) and control. It is said that the advantage of this system is achieved if the predictions using a single training set are only developed for few objects. This can be demonstrated in the case of the k-NN technique, which is instance-based and function is only estimated locally. == Disadvantages == Theoretical disadvantages with lazy learning include: The large space requirement to store the entire training dataset. In practice, this is not an issue because of advances in hardware and the relatively small number of attributes (e.g., as co-occurrence frequency) that need to be stored. Particularly noisy training data increases the case base unnecessarily, because no abstraction is made during the training phase. In practice, as stated earlier, lazy learning is applied to situations where any learning performed in advance soon becomes obsolete because of changes in the data. Also, for the problems for which lazy learning is optimal, "noisy" data does not really occur - the purchaser of a book has either bought another book or hasn't. Lazy learning methods are usually slower to evaluate. In practice, for very large databases with high concurrency loads, the queries are not postponed until actual query time, but recomputed in advance on a periodic basis - e.g., nightly, in anticipation of future queries, and the answers stored. This way, the next time new queries are asked about existing entries in the database, the answers are merely looked up rapidly instead of having to be computed on the fly, which would almost certainly bring a high-concurrency multi-user system to its knees. Larger training data also entail increased cost. Particularly, there is the fixed amount of computational cost, where a processor can only process a limited amount of training data points. There are standard techniques to improve re-computation efficiency so that a particular answer is not recomputed unless the data that impact this answer has changed (e.g., new items, new purchases, new views). In other words, the stored answers are updated incrementally. This approach, used by large e-commerce or media sites, has long been used in the Entrez portal of the National Center for Biotechnology Information (NCBI) to precompute similarities between the different items in its large datasets: biological sequences, 3-D protein structures, published-article abstracts, etc. Because "find similar" queries are asked so frequently, the NCBI uses highly parallel hardware to perform nightly recomputation. The recomputation is performed only for new entries in the datasets against each other and against existing entries: the similarity between two existing entries need not be recomputed. == Examples of Lazy Learning Methods == K-nearest neighbors, which is a special case of instance-based learning. Local regression. Lazy naive Bayes rules, which are extensively used in commercial spam detection software. Here, the spammers keep getting smarter and revising their spamming strategies, and therefore the learning rules must also be continually updated.

  Read more →
• 

  Logistics automation

  Logistics automation is the application of computer software or automated machinery to logistics operations in order to improve its efficiency. Typically this refers to operations within a warehouse or distribution center, with broader tasks undertaken by supply chain engineering systems and enterprise resource planning systems. Logistics automation systems can powerfully complement the facilities provided by these higher level computer systems. The focus on an individual node within a wider logistics network allows systems to be highly tailored to the requirements of that node. == Components == Logistics automation systems comprise a variety of hardware and software components: Fixed machinery Automated storage and retrieval systems, including: Cranes serve a rack of locations, allowing many levels of stock to be stacked vertically, and allowing for higher storage densities and better space utilization than alternatives. In systems produced by Amazon Robotics, automated guided vehicles move items to a human picker. Conveyors: Containers can enter automated conveyors in one area of the warehouse and, either through hard-coded rules or data input, be moved to a selected destination. Vertical carousels based on the paternoster lift system or using space optimization, similar to vending machines, but on a larger scale. Sortation systems: similar to conveyors but typically with higher capacity and able to divert containers more quickly. Typically used to distribute high volumes of small cartons to a large set of locations. Industrial robots: four- to six-axis industrial robots, e.g. palletizing robots, are used for palletizing, depalletizing, packaging, commissioning and order picking. Typically all of these will automatically identify and track containers using barcodes or, increasingly, RFID tags. Motion check weighers may be used to reject cases or individual products that are under or over their specified weight. They are often used in kitting conveyor lines to ensure all pieces belonging in the kit are present. Mobile technology Radio data terminals: these are handheld or truck-mounted terminals which connect by radio to logistics automation software and provide instructions to operators moving throughout the warehouse. Many also have barcode scanners to allow identification of containers more quickly and accurately than manual keyboard entry. Software Integration software: this provides overall control of the automation machinery and allows cranes to be connected to conveyors for seamless stock movements. Operational control software: provides low-level decision-making, such as where to store incoming containers, and where to retrieve them when requested. Business control software: provides higher-level functionality, such as identification of incoming deliveries/stock, scheduling order fulfillment, and assignment of stock to outgoing trailers. == Benefits == A typical warehouse or distribution center will receive stock of a variety of products from suppliers and store these until the receipt of orders from customers, whether individual buyers (e.g. mail order), retail branches (e.g. chain stores), or other companies (e.g. wholesalers). A logistics automation system may provide the following: Automated goods in processes: Incoming goods can be marked with barcodes and the automation system notified of the expected stock. On arrival, the goods can be scanned and thereby identified, and taken via conveyors, sortation systems, and automated cranes into an automatically assigned storage location. Automated goods retrieval for orders: On receipt of orders, the automation system is able to immediately locate goods and retrieve them to a pick-face location. Automated dispatch processing: Combining knowledge of all orders placed at the warehouse the automation system can assign picked goods into dispatch units and then into outbound loads. Sortation systems and conveyors can then move these onto the outgoing trailers. If needed, repackaging to ensure proper protection for further distribution or to change the package format for specific retailers/customers. A complete warehouse automation system can drastically reduce the workforce required to run a facility, with human input required only for a few tasks, such as picking units of product from a bulk packed case. Even here, assistance can be provided with equipment such as pick-to-light units. Smaller systems may only be required to handle part of the process. Examples include automated storage and retrieval systems, which simply use cranes to store and retrieve identified cases or pallets, typically into a high-bay storage system which would be unfeasible to access using fork-lift trucks or any other means. The use of Automatic Guided Vehicles maximizes the output compared to humans since they can do repetitive tasks for long hours and with least to no supervision. An AGV is built and programmed for precision and accuracy thereby reducing the chances of errors in a warehouse, especially when dealing with fragile goods. == Automation software == Software or cloud-based SaaS solutions are used for logistics automation which helps the supply chain industry in automating the workflow as well as management of the system. Knowledge @ Wharton staff writers noted in 2011 that some manufacturers and retailers were weathering the Great Recession "by signing up for pay-as-you-go logistics services available through the Internet 'cloud'". They identified the benefits and reduced costs which came from sharing information about shipments with suppliers, hauliers and end users. There is little generalized software available in this market. This is because there is no rule to generalize the system as well as work flow even though the practice is more or less the same. Most of the commercial companies do use one or the other of the custom solutions. But there are various software solutions that are being used within the departments of logistics. There are a few departments in Logistics, namely: Conventional Department, Container Department, Warehouse, Marine Engineering, Heavy Haulage, etc. Software used in these departments Conventional department : CVT software / CTMS software. Container Trucking: CTMS software Warehouse : WMS/WCS Improving Effectiveness of Logistics Management Logistical Network Information Transportation Sound Inventory Management Warehousing, Materials Handling & Packaging

  Read more →
• 

  Agentive logic

  Agentive logic (also called the logic of action or logic of agency) is the field of philosophical logic and logic in computer science that studies formal representations of agents, their actions, and their abilities. An agentive logic in the narrower sense is a formal system whose primitive operators express that an agent does something, can do something, or sees to it that something is the case. Agentive logics generalise modal logic by adding modalities indexed to agents and to actions. Typical examples include: STIT logics (from sees to it that) with operators of the form [ i s t i t : φ ] {\displaystyle [i\ {\mathsf {stit}}:\varphi ]} meaning that agent i {\displaystyle i} sees to it that φ {\displaystyle \varphi } holds; dynamic logics of action with program-like modalities [ α ] φ {\displaystyle [\alpha ]\varphi } and ⟨ α ⟩ φ {\displaystyle \langle \alpha \rangle \varphi } meaning, roughly, that after every (respectively, some) execution(s) of action α {\displaystyle \alpha } , φ {\displaystyle \varphi } holds; logics with explicit agentive operators such as "can do", "brings about", or "is able to ensure". Agentive logics are used in action theory in philosophy, in the semantics of natural language, in the theory of program verification, and in artificial intelligence, where they underpin formalisms for reasoning about actions, planning, and intelligent agents. == Terminology and scope == The adjective agentive derives from the Latin agens ("one who acts") and originally referred to the grammatical agent of a verb. In logical contexts it designates operators or predicates whose primary argument position is an agent rather than a proposition alone, for example A i φ {\displaystyle A_{i}\varphi } ("agent i {\displaystyle i} does φ {\displaystyle \varphi } ") or C i φ {\displaystyle C_{i}\varphi } ("agent i {\displaystyle i} can bring about φ {\displaystyle \varphi } "). In contemporary literature, agentive logic is sometimes used narrowly for formal reconstructions of St. Anselm's modal account of facere ("to do"). More broadly, the term is used interchangeably with logic of action or logic of agency to cover a family of modal and dynamic logics designed to capture the structure of action and choice. == Historical background == === Medieval and early modern roots === Medieval logicians already explored analogies between modalities of action and alethic modalities such as possibility and necessity, for instance, in discussions of obligation and power. An influential early agentive analysis is due to St. Anselm (11th century), who treated "doing φ {\displaystyle \varphi } " as a kind of modal operator on propositions, anticipating later modal logics of agency. Modern reconstructions of Anselm's theory show that the resulting "agentive logic" can be modelled with neighbourhood semantics and satisfies a recognisable square of opposition. === Modern logic of action === Modern study of the logic of action began in the mid-20th century, parallel to developments in deontic logic and tense logic. Early systems were proposed by Georg Henrik von Wright, Stig Kanger, and others, often motivated by questions about norms and responsibility. From the 1960s onward, two largely independent but eventually converging traditions emerged: a branching-time tradition, culminating in STIT logics, emphasising agents' choices among possible futures; and dynamic logics of programs and actions, developed within computer science to reason about program execution. In the 1990s and 2000s, action logics were further developed in connection with knowledge representation, planning, and multi-agent systems in AI, and with dynamic and update semantics in linguistics. == Core ideas == Despite their diversity, most agentive logics share some general themes: Agents are treated as explicit indices of modal operators, as in [ i d o e s ] φ {\displaystyle [i\ {\mathsf {does}}]\varphi } or C i φ {\displaystyle C_{i}\varphi } . Actions are represented either implicitly, via changes between possible worlds along an accessibility relation, or explicitly, as terms denoting primitive and composite actions. Choice and ability are captured by modalities describing what an agent can ensure, usually relative to assumptions about the environment and other agents. Formal properties such as closure under composition, interaction between different agents, and connections to obligation (what an agent ought to do) and knowledge (what an agent knows how to do) are investigated. == STIT logics == STIT ("sees to it that") logics, originating in work by Nuel Belnap and collaborators, treat agency in a branching-time framework. A STIT model consists of a partially ordered set of moments with a tree-like structure, sets of histories (maximal branches through the tree), and for each agent at each moment, a partition of the histories through that moment representing the choices available to the agent. Intuitively, an agent's action at a moment determines which equivalence class (choice cell) of histories becomes actual; a formula [ i s t i t : φ ] {\displaystyle [i\ {\mathsf {stit}}:\varphi ]} is true at a history–moment pair if φ {\displaystyle \varphi } holds on all histories in the choice cell corresponding to the agent's current action. Different STIT operators have been distinguished, notably: the Chellas STIT operator, often written [ i c s t i t : φ ] {\displaystyle [i\ {\mathsf {cstit}}:\varphi ]} , which requires only that the agent's choice guarantees φ {\displaystyle \varphi } ; and the deliberative STIT operator, [ i d s t i t : φ ] {\displaystyle [i\ {\mathsf {dstit}}:\varphi ]} , which additionally requires that φ {\displaystyle \varphi } is not already historically necessary. STIT frameworks have been extended with group agency operators, temporal modalities, epistemic operators, and deontic operators to study responsibility, collective action, and obligations under indeterminism. == Dynamic logics of action == Dynamic logic was originally developed to reason about the behaviour of computer programs, treating program execution as a kind of action. In propositional dynamic logic (PDL), action terms α , β , … {\displaystyle \alpha ,\beta ,\dots } denote abstract programs or actions, and formulas of the form [ α ] φ {\displaystyle [\alpha ]\varphi } and ⟨ α ⟩ φ {\displaystyle \langle \alpha \rangle \varphi } express that all, respectively some, terminating executions of α {\displaystyle \alpha } lead to states where φ {\displaystyle \varphi } holds. From the standpoint of agentive logic, dynamic logic provides: a language for building complex actions from primitives via sequencing, choice, and iteration (e.g., α ; β {\displaystyle \alpha ;\beta } , α ∪ β {\displaystyle \alpha \cup \beta } , α ∗ {\displaystyle \alpha ^{}} ); a Kripke semantics in which actions correspond to labelled accessibility relations; and proof systems (such as Hoare logic and weakest precondition calculi) for reasoning about the correctness of action sequences. Extensions such as concurrent dynamic logic add operators for parallel composition, allowing reasoning about interacting processes and concurrent actions. John-Jules Ch. Meyer and others have argued that dynamic logic is a natural base for logics of agents, by adding modalities for knowledge, belief, and ability on top of the action modalities. Dynamic logics have also been applied to normative reasoning, yielding dynamic deontic logics where actions are related to obligations and permissions, and to dynamic epistemic logics in which information-changing actions such as announcements are modelled as programs. == Situation calculus and other action formalisms == In artificial intelligence, reasoning about action and change is often based on first-order languages that explicitly represent situations, events, and fluents (time-varying properties). The best known is situation calculus, introduced by John McCarthy and developed extensively by Raymond Reiter. In such formalisms: action terms name primitive actions; a function symbol (often d o {\displaystyle {\mathsf {do}}} ) maps an action and a situation to a successor situation; and axioms describe which fluents hold in which situations and how actions change them. Reiter's successor state axioms give compact specifications of how each fluent changes under all actions, and precondition axioms specify when actions are possible. Related formalisms include the event calculus and fluent calculus, which provide alternative ways of representing events and their effects. While these systems are often first-order rather than modal, they are closely related to agentive logics: their action terms and transition structures can be seen as providing models for dynamic or STIT-style modalities, and conversely, dynamic logics can be used as abstract specification languages for such AI formalisms. == Ability, agency, and related modalities == Many agentive logics introduce explicit operators for ability or "can-do"

  Read more →
• 

  Wadhwani Institute for Artificial Intelligence

  Wadhwani AI, based in Mumbai, Maharashtra, is an independent, non-profit institute. Founded in 2018, it is dedicated to developing Artificial intelligence solutions for social good. Their mission is to build AI-based innovations and solutions for underserved communities in developing countries, for a wide range of domains including agriculture, education, financial inclusion, healthcare, and infrastructure. == History and funding == The institute was founded with a $30 million philanthropic effort by the Wadhwani brothers, Romesh Wadhwani and Sunil Wadhwani. The institute was inaugurated and dedicated to the nation by Narendra Modi, the 14th Prime Minister of India. In 2019, the institute received a $2 million grant from Google.org to create technologies to help reduce crop losses in cotton farming, through integrated pest management. The United States Agency for International Development awarded $2 million to the institute in 2020 to develop tools, using mathematical modeling techniques and digital technologies such as artificial intelligence and machine learning, to forecast COVID-19 disease patterns, estimate resources needed, and plan interventions. == Collaboration == With assistance from Google, the Ministry of Agriculture and Farmers' Welfare and the Wadhwani AI developed Krishi 24/7, the first AI-powered automated agricultural news monitoring and analysis tool. Through better decision-making, Krishi 24/7 will support the identification of valuable news, provide timely notifications, and respond quickly to safeguard farmers' interests and advance sustainable agricultural growth. The application converts news articles into English after scanning them in several languages. It ensures that the ministry is informed in a timely manner about pertinent occurrences that are published online by extracting key information from news items, including the headline, crop name, event type, date, location, severity, summary, and source link. The National Center for Disease Control has effectively implemented a comparable automated surveillance and analysis tool for disease outbreaks.

  Read more →
• 

  Audio inpainting

  Audio inpainting (also known as audio interpolation) is an audio restoration task which deals with the reconstruction of missing or corrupted portions of a digital audio signal. Inpainting techniques are employed when parts of the audio have been lost due to various factors such as transmission errors, data corruption or errors during recording. The goal of audio inpainting is to fill in the gaps (i.e., the missing portions) in the audio signal seamlessly, making the reconstructed portions indistinguishable from the original content and avoiding the introduction of audible distortions or alterations. Many techniques have been proposed to solve the audio inpainting problem and this is usually achieved by analyzing the temporal and spectral information surrounding each missing portion of the considered audio signal. Classic methods employ statistical models or digital signal processing algorithms to predict and synthesize the missing or damaged sections. Recent solutions, instead, take advantage of deep learning models, thanks to the growing trend of exploiting data-driven methods in the context of audio restoration. Depending on the extent of the lost information, the inpainting task can be divided in three categories. Short inpainting refers to the reconstruction of few milliseconds (approximately less than 10) of missing signal, that occurs in the case of short distortions such as clicks or clipping. In this case, the goal of the reconstruction is to recover the lost information exactly. In long inpainting instead, with gaps in the order of hundreds of milliseconds or even seconds, this goal becomes unrealistic, since restoration techniques cannot rely on local information. Therefore, besides providing a coherent reconstruction, the algorithms need to generate new information that has to be semantically compatible with the surrounding context (i.e., the audio signal surrounding the gaps). The case of medium duration gaps lays between short and long inpainting. It refers to the reconstruction of tens of millisecond of missing data, a scale where the non-stationary characteristic of audio already becomes important. == Definition == Consider a digital audio signal x {\displaystyle \mathbf {x} } . A corrupted version of x {\displaystyle \mathbf {x} } , which is the audio signal presenting missing gaps to be reconstructed, can be defined as x ~ = m ∘ x {\displaystyle \mathbf {\tilde {x}} =\mathbf {m} \circ \mathbf {x} } , where m {\displaystyle \mathbf {m} } is a binary mask encoding the reliable or missing samples of x {\displaystyle \mathbf {x} } , and ∘ {\displaystyle \circ } represents the element-wise product. Audio inpainting aims at finding x ^ {\displaystyle \mathbf {\hat {x}} } (i.e., the reconstruction), which is an estimation of x {\displaystyle \mathbf {x} } . This is an ill-posed inverse problem, which is characterized by a non-unique set of solutions. For this reason, similarly to the formulation used for the inpainting problem in other domains, the reconstructed audio signal can be found through an optimization problem that is formally expressed as x ^ ∗ = argmin X ^ L ( m ∘ x ^ , x ~ ) + R ( x ^ ) {\displaystyle \mathbf {\hat {x}} ^{}={\underset {\hat {\mathbf {X} }}{\text{argmin}}}~L(\mathbf {m} \circ \mathbf {\hat {x}} ,\mathbf {\tilde {x}} )+R(\mathbf {\hat {x}} )} . In particular, x ^ ∗ {\displaystyle \mathbf {\hat {x}} ^{}} is the optimal reconstructed audio signal and L {\displaystyle L} is a distance measure term that computes the reconstruction accuracy between the corrupted audio signal and the estimated one. For example, this term can be expressed with a mean squared error or similar metrics. Since L {\displaystyle L} is computed only on the reliable frames, there are many solutions that can minimize L ( m ∘ x ^ , x ~ ) {\displaystyle L(\mathbf {m} \circ \mathbf {\hat {x}} ,\mathbf {\tilde {x}} )} . It is thus necessary to add a constraint to the minimization, in order to restrict the results only to the valid solutions. This is expressed through the regularization term R {\displaystyle R} that is computed on the reconstructed audio signal x ^ {\displaystyle \mathbf {\hat {x}} } . This term encodes some kind of a-priori information on the audio data. For example, R {\displaystyle R} can express assumptions on the stationarity of the signal, on the sparsity of its representation or can be learned from data. == Techniques == There exist various techniques to perform audio inpainting. These can vary significantly, influenced by factors such as the specific application requirements, the length of the gaps and the available data. In the literature, these techniques are broadly divided in model-based techniques (sometimes also referred as signal processing techniques) and data-driven techniques. === Model-based techniques === Model-based techniques involve the exploitation of mathematical models or assumptions about the underlying structure of the audio signal. These models can be based on prior knowledge of the audio content or statistical properties observed in the data. By leveraging these models, missing or corrupted portions of the audio signal can be inferred or estimated. An example of a model-based techniques are autoregressive models. These methods interpolate or extrapolate the missing samples based on the neighboring values, by using mathematical functions to approximate the missing data. In particular, in autoregressive models the missing samples are completed through linear prediction. The autoregressive coefficients necessary for this prediction are learned from the surrounding audio data, specifically from the data adjacent to each gap. Some more recent techniques approach audio inpainting by representing audio signals as sparse linear combinations of a limited number of basis functions (as for example in the Short Time Fourier Transform). In this context, the aim is to find the sparse representation of the missing section of the signal that most accurately matches the surrounding, unaffected signal. The aforementioned methods exhibit optimal performance when applied to filling in relatively short gaps, lasting only a few tens of milliseconds, and thus they can be included in the context of short inpainting. However, these signal-processing techniques tend to struggle when dealing with longer gaps. The reason behind this limitation lies in the violation of the stationarity condition, as the signal often undergoes significant changes after the gap, making it substantially different from the signal preceding the gap. As a way to overcome these limitations, some approaches add strong assumptions also about the fundamental structure of the gap itself, exploiting sinusoidal modeling or similarity graphs to perform inpainting of longer missing portions of audio signals. === Data-driven techniques === Data-driven techniques rely on the analysis and exploitation of the available audio data. These techniques often employ deep learning algorithms that learn patterns and relationships directly from the provided data. They involve training models on large datasets of audio examples, allowing them to capture the statistical regularities present in the audio signals. Once trained, these models can be used to generate missing portions of the audio signal based on the learned representations, without being restricted by stationarity assumptions. Data-driven techniques also offer the advantage of adaptability and flexibility, as they can learn from diverse audio datasets and potentially handle complex inpainting scenarios. As of today, such techniques constitute the state-of-the-art of audio inpainting, being able to reconstruct gaps of hundreds of milliseconds or even seconds. These performances are made possible by the use of generative models that have the capability to generate novel content to fill in the missing portions. For example, generative adversarial networks, which are the state-of-the-art of generative models in many areas, rely on two competing neural networks trained simultaneously in a two-player minmax game: the generator produces new data from samples of a random variable, the discriminator attempts to distinguish between generated and real data. During the training, the generator's objective is to fool the discriminator, while the discriminator attempts to learn to better classify real and fake data. In GAN-based inpainting methods the generator acts as a context encoder and produces a plausible completion for the gap only given the available information surrounding it. The discriminator is used to train the generator and tests the consistency of the produced inpainted audio. Recently, also diffusion models have established themselves as the state-of-the-art of generative models in many fields, often beating even GAN-based solutions. For this reason they have also been used to solve the audio inpainting problem, obtaining valid results. These models generate new data instances by inverting the

  Read more →
• 

  Computer security

  Computer security (also cybersecurity, digital security, or information technology (IT) security) is a subdiscipline within the field of information security. It focuses on protecting computer software, systems, and networks from threats that can lead to unauthorized information disclosure, theft, or damage to hardware, software, or data, as well as to the disruption or misdirection of the services they provide. The growing significance of computer security reflects the increasing dependence on computer systems, the Internet, and evolving wireless network standards. This reliance has expanded with the proliferation of smart devices, including smartphones, televisions, and other components of the Internet of things (IoT). As digital infrastructure becomes more embedded in everyday life, cybersecurity has emerged as a critical concern. The complexity of modern information systems—and the societal functions they underpin—has introduced new vulnerabilities. Systems that manage essential services, such as power grids, electoral processes, and finance, are particularly sensitive to security breaches. Although many aspects of computer security involve digital security, such as electronic passwords and encryption, physical security measures, such as metal locks, are still used to prevent unauthorized tampering. IT security is not a perfect subset of information security and therefore does not completely align with the security convergence schema. == Vulnerabilities and attacks == A vulnerability refers to a flaw in the structure, execution, functioning, or internal oversight of a computer or system that compromises its security. Most of the vulnerabilities that have been discovered are documented in the Common Vulnerabilities and Exposures (CVE) database. An exploitable vulnerability is one for which at least one working exploit exists. Actors maliciously seeking vulnerabilities are known as threats. Vulnerabilities can be researched, reverse-engineered, hunted, or exploited using automated tools or customized scripts. Various people or parties are vulnerable to cyberattacks; however, different groups are likely to experience different types of attacks more than others. In April 2023, the United Kingdom Department for Science, Innovation & Technology released a report on cyberattacks over the previous 12 months. They surveyed 2,263 UK businesses, 1,174 UK registered charities, and 554 education institutions. The research found that "32% of businesses and 24% of charities overall recall any breaches or attacks from the last 12 months." These figures were much higher for "medium businesses (59%), large businesses (69%), and high-income charities with £500,000 or more in annual income (56%)." Yet, although medium or large businesses are more often the victims, since larger companies have generally improved their security over the last decade, small and midsize businesses (SMBs) have also become increasingly vulnerable as they often "do not have advanced tools to defend the business." SMBs are most likely to be affected by malware, ransomware, phishing, man-in-the-middle attacks, and Denial-of Service (DoS) Attacks. Normal internet users are most likely to be affected by untargeted cyberattacks. These are where attackers indiscriminately target as many devices, services, or users as possible. They do this using techniques that take advantage of the openness of the Internet. These strategies mostly include phishing, ransomware, water holing and scanning. To secure a computer system, it is important to understand the attacks that can be made against it, and these threats can typically be classified into one of the following categories: === Backdoor === A backdoor in a computer system, a cryptosystem or an algorithm, is any secret method of bypassing normal authentication or security controls. These weaknesses may exist for many reasons, including original design or poor configuration. Due to the nature of backdoors, they are of greater concern to companies and databases as opposed to individuals. Backdoors may be added by an authorized party to allow some legitimate access or by an attacker for malicious reasons. Criminals often use malware to install backdoors, giving them remote administrative access to a system. Once they have access, cybercriminals can "modify files, steal personal information, install unwanted software, and even take control of the entire computer." Backdoors can be difficult to detect, as they often remain hidden within source code or system firmware and may require intimate knowledge of the operating system to identify. === Denial-of-service attack === Denial-of-service attacks (DoS) are designed to make a machine or network resource unavailable to its intended users. Attackers can deny service to individual victims, such as by deliberately entering an incorrect password enough consecutive times to cause the victim's account to be locked, or they may overload the capabilities of a machine or network and block all users at once. While a network attack from a single IP address can be blocked by adding a new firewall rule, many forms of distributed denial-of-service (DDoS) attacks are possible, where the attack comes from a large number of points. In this case, defending against these attacks is much more difficult. Such attacks can originate from the zombie computers of a botnet or from a range of other possible techniques, including distributed reflective denial-of-service (DRDoS), where innocent systems are fooled into sending traffic to the victim. With such attacks, the amplification factor makes the attack easier for the attacker because they have to use little bandwidth themselves. To understand why attackers may carry out these attacks, see the 'attacker motivation' section. === Physical access attacks === A direct-access attack is when an unauthorized user (an attacker) gains physical access to a computer, typically to copy data from it or steal information. Attackers may also compromise security by making operating system modifications, installing software worms, keyloggers, covert listening devices or using wireless microphones. Even when the system is protected by standard security measures, these may be bypassed by booting another operating system or tool from a CD-ROM or other bootable media. Disk encryption and the Trusted Platform Module standard are designed to prevent these attacks. Direct service attackers are related in concept to direct memory attacks which allow an attacker to gain direct access to a computer's memory. The attacks "take advantage of a feature of modern computers that allows certain devices, such as external hard drives, graphics cards, or network cards, to access the computer's memory directly." === Eavesdropping === Eavesdropping is the act of surreptitiously listening to a private computer conversation (communication), usually between hosts on a network. It typically occurs when a user connects to a network where traffic is not secured or encrypted and sends sensitive business data to a colleague, which, when listened to by an attacker, could be exploited. Data transmitted across an open network can be intercepted by an attacker using various methods. Unlike malware, direct-access attacks, or other forms of cyberattacks, eavesdropping attacks are unlikely to negatively affect the performance of networks or devices, making them difficult to notice. In fact, "the attacker does not need to have any ongoing connection to the software at all. The attacker can insert the software onto a compromised device, perhaps by direct insertion or perhaps by a virus or other malware, and then come back some time later to retrieve any data that is found or trigger the software to send the data at some determined time." Using a virtual private network (VPN), which encrypts data between two points, is one of the most common forms of protection against eavesdropping. Using the best form of encryption possible for wireless networks is best practice, as well as using HTTPS instead of an unencrypted HTTP. Programs such as Carnivore and NarusInSight have been used by the Federal Bureau of Investigation (FBI) and the NSA to eavesdrop on the systems of internet service providers. Even machines that operate as a closed system (i.e., with no contact with the outside world) can be eavesdropped upon by monitoring the faint electromagnetic transmissions generated by the hardware. TEMPEST is a specification by the NSA referring to these attacks. === Malware === Malicious software (malware) is any software code or computer program "intentionally written to harm a computer system or its users." Once present on a computer, it can leak sensitive details such as personal information, business information and passwords, can give control of the system to the attacker, and can corrupt or delete data permanently. ==== Types of malware ==== Viruses are a specific type of malware, and are normally a malicious code that hijac

  Read more →
• 

  United States Tech Force

  The U.S. Tech Force (also styled as US Tech Force, Tech Force, or Government Tech Force) is a federal hiring initiative launched by the second Donald Trump administration in December 2025. The program, administered by the Office of Personnel Management (OPM), aims to recruit about 1,000 early-career technology professionals into two-year government jobs to modernize federal IT systems, advance artificial intelligence (AI) capabilities, and address technological gaps in government operations. The initiative is an effort to plug capability gaps created by Trump-administration efforts to shrink the federal government, which led to the departure of some 220,000 federal employees, including many in IT. The initiative seeks early-career workers; officials said it would offer competitive salaries and opportunities to work on high-impact government technology projects. Major technology companies—including Amazon, Apple, Microsoft, Nvidia, Meta, Google, and OpenAI—agreed to help identify and refer candidates. Candidates are allowed to take Tech Force positions on leaves of absence and without divesting their stock, raising conflict-of-interest questions. In January 2026, OPM direction Scott Kupor said the deadline for applying to Tech Force was being extended because of "tremendous interest" without saying how many people had actually applied. Also in December 2025, news broke that the administration is planning another novel use of private-sector workers: hiring cybersecurity firms for offensive cyber operations.

  Read more →
• 

  Organoid intelligence

  Organoid intelligence (OI) is an emerging field of study in computer science and biology that develops and studies biological wetware computing using 3D cultures of human brain cells (or brain organoids) and brain-machine interface technologies. Such technologies may be referred to as OIs or the nervous filesystem. Organoid intelligent computer systems can be an example of biohybrid systems. == Differences with non-organic computing == As opposed to traditional non-organic silicon-based approaches, OI seeks to use lab-grown cerebral organoids to serve as "biological hardware". While these structures are still far from being able to think like a regular human brain and do not yet possess strong computing capabilities, OI research currently offers the potential to improve the understanding of brain development, learning and memory, potentially finding treatments for neurological disorders such as dementia. Thomas Hartung, a professor from Johns Hopkins University, argued in 2023 that "while silicon-based computers are certainly better with numbers, brains are better at learning." He noted that transistor density in computer chip may be approaching its limits, whereas brains, being wired differently, are more energy-efficient and can store large amounts of information. Some researchers claim that even though human brains are slower than machines at processing simple information, they are far better at processing complex information as brains can deal with fewer and more uncertain data, perform both sequential and parallel processing, being highly heterogenous, use incomplete datasets, and is said to outperform non-organic machines in decision-making. Training OIs involve the process of biological learning (BL) as opposed to machine learning (ML) for AIs. == Bioinformatics in OI == OI generates complex biological data, necessitating sophisticated methods for processing and analysis. Bioinformatics provides the tools and techniques to decipher raw data, uncovering the patterns and insights. Researchers have developed a platform named Neuroplatform for experimenting remotely with brain organoids via an API. == Intended functions == Brain-inspired computing hardware aims to emulate the structure and working principles of the brain and could be used to address current limitations in AI technologies. However, brain-inspired silicon chips are still limited in their ability to fully mimic brain function, as most examples are built on digital electronic principles. One study performed OI computation (which they termed Brainoware) by sending and receiving information from the brain organoid using a high-density multielectrode array. By applying spatiotemporal electrical stimulation, nonlinear dynamics, and fading memory properties, as well as unsupervised learning from training data by reshaping the organoid functional connectivity, the study showed the potential of this technology by using it for speech recognition and nonlinear equation prediction in a reservoir computing framework. == Ethical concerns == While researchers are hoping to use OI and biological computing to complement traditional silicon-based computing, there are also questions about the ethics of such an approach. Concerns include the possibility that an organoid could develop sentience or consciousness, and the question of the relationship between a stem cell donor (for growing the organoid) and the respective OI system.

  Read more →