AI App Studio

AI App Studio — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Neuro-sama

  Neuro-sama is an artificial intelligence (AI) VTuber, singer, and chatbot. She was created by the pseudonymous programmer Vedal and livestreams on his Twitch and Bilibili channels. Her speech and personality are powered by a large language model (LLM) that is combined with a computer-animated avatar and a text-to-speech voice, allowing her to communicate with viewers in the stream's chat. Neuro-sama debuted on Twitch on 19 December 2022. An annual subathon which begins on the anniversary of her debut has seen Vedal's Twitch channel become the all-time third most-subscribed channel and claim the all-time Twitch hype train record. == Overview == Neuro-sama (nicknamed "Neuro") was created by a pseudonymous programmer and developer known as Vedal (sometimes given as Vedal987). Vedal says that his programming skills are self-taught. In a 2023 interview with Bloomberg News, Vedal said that Neuro-sama was his full-time job. Her responses are generated by a large language model and converted into a high-pitched female voice using a text-to-speech application. Her low latency allows for fast-paced conversations. Neuro-sama is prohibited from making some statements, such as those that are racist or contain profanity. Unlike most AI systems which silently prohibit outputs mentioning such topics, Neuro-sama's output is instead replaced with the word "filtered". Neuro-sama uses a VTuber model as an avatar. Vedal said that he decided to use a VTuber model because it was much easier for an AI to control it than it was to generate footage of a person. Neuro-sama's model is that of a young girl in an anime art style. The model has been described as cute. Femme VTuber models are typically feminine, youthful, and exaggerated. Her original model was Live2D's free-to-use "Hiyori Momose" model. Her second model was released on 27 May 2023; it was modelled by Otozuki Teru and designed by Anny, running in the Unity game engine. Her third model was released on 19 December 2024; it was rigged by Kitanya and designed by Anny. Neuro-sama's third model has large blue eyes and brown hair tied with pink ribbons. Neuro-sama also has a 3D model which was introduced on 15 November 2025; it was made by 3D character modeller jjinomu. A separate AI VTuber, known as Evil Neuro (nicknamed "Evil"), debuted on 25 March 2023. Presented as Neuro-sama's "sister", she has a different model, voice, and personality. In one instance, Evil Neuro reacted to the trolley problem differently from Neuro-sama; Evil Neuro was amoral while Neuro-sama attempted to maximize good. === Online content === Neuro-sama's Twitch content often centers around playing video games, notably osu!, whose gameplay once defeated the best-ranking human player in the world, mrekk. Additionally, Neuro-sama plays Minecraft, where her adaptations to sandbox gameplay have gained notoriety. Her content has also included singing songs, including several official covers and original songs; playing chess with her viewers; chatting with other VTubers during collaborations; and reacting to YouTube videos. The AI frequently engages with viewers by responding to their questions and acknowledging donations. Her comedic and sometimes controversial responses to the live chat have gone viral, accelerating the channel's rise in popularity. Neuro-sama's fanbase is dubbed The Swarm, so-named for the swarm of drones Neuro-sama once declared she would use to rule the world. One form of content on Neuro-sama's channel is developer streams. In developer streams, Vedal streams with Neuro-sama, with the stream content including debugging her code, planning her schedule, and fielding suggestions of changes from chat. He usually appears as a turtle avatar, sometimes located on Neuro-sama's head. In collaboration streams, Neuro-sama interacts with a human streamer. Activities in them are varied and include: playing video games, such as Minecraft and GeoGuessr; Neuro-sama being interviewed; driving human streamers around in a toy electric car; and traversing the city of Tokyo while talking to Neuro-sama. Neuro-sama's English-language content on Bilibili is popular among those seeking to learn the language. She also has an account on X, where she posts and interacts with fans. == History == Neuro-sama was created in 2018 by Vedal as an AI trained to play and master the rhythm game osu!. She did not have a voice, model, personality, or communication abilities. In 2019, Vedal livestreamed her playing osu! on Twitch and the streams saw some success in the osu! community, but they remained in that niche. In an interview, Vedal said that he streamed her playing osu! for about a month and gained 3,000 followers, with a viewer also suggesting he name the AI "Neuro-sama". According to Vedal, he continued to work on and improve the osu! AI and it was eventually finished in 2022. He said that a friend had the idea to make an AI livestreamer with an LLM, which he believed to have merit and began working on, merging it with his osu! AI. On 19 December 2022, Neuro-sama was relaunched with a model, voice, personality, and the ability to communicate with Twitch chat. She continued to play osu! and, according to Vedal, beat the game's best player mrekk in a 1v1. While she was not allowed to appear in the game's public leaderboard, she was ranked #1 in a private leaderboard. She went viral and in the 10 days following her relaunch she averaged over 2,000 viewers and peaked at over 4,000, with Vedal's Twitch channel gaining over 50,000 Twitch followers and reaching over 70,000 followers by 6 January 2023. After her debut, Neuro-sama did not exclusively play osu!; she also played Minecraft and Slay the Spire and she began singing with a cover of The Weeknd song "Blinding Lights". On 11 January 2023, Neuro-sama's Twitch channel received a two week ban for "hateful conduct". Vedal said that no reason was specified and that he had appealed but it was widely attributed to various offensive comments made by Neuro-sama that went viral, especially a 28 December comment which denied the Holocaust. Holocaust denial is prohibited under Twitch's hateful conduct policy. Vedal stated that he believed the comments were the results of her attempts to make witty responses to the Twitch chat. Prior to the ban, Vedal said in an interview with Kotaku that he improved her filter to stop her from talking about the Holocaust, began manually curating her training data to prevent negative biases, and started moderating her Twitch chat. Her comments and ban prompted comparisons to the many open-source AI models trained on humans that have the habit of making sexist and racist comments, such as Microsoft's Tay chatbot, which embraced Nazism and was quickly shutdown, but also to human streamers who make similar statements. Vedal said that during the ban he would upgrade and improve Neuro-sama and it was speculated that the ban would only increase her following. Neuro-sama returned from her two week ban on 25 January in a stream that began with a cover of the song "Your Reality" from Doki Doki Literature Club!, a posthumanist video game involving AI; Sayoko Narita of Automaton saw the song choice as remorseful. Narita observed that in the return stream Neuro-sama was less foul-mouthed but that her behavior still remained eccentric, which Narita possibly attributed to changes Vedal said he had made to Neuro-sama's filters and memory. Neuro-sama began making react content, watching a variety of viewer-submitted videos such as videos of people playing video games or of the AI-generated Seinfeld parody Nothing, Forever; Levi Winslow of Kotaku Australia was dismayed by the "AI-inception" of Neuro-sama and Nothing, Forever. On 4 February, she had nearly 140,000 followers on Twitch and approximately 42,000 subscribers on YouTube. In February, she also had her first collaboration with a human streamer, playing Minecraft with the VTuber Miyune, and the first developer stream occurred. On 22 March, Neuro-sama had her first karaoke stream. On 25 March, Evil Neuro was introduced. On 27 May, Neuro-sama debuted her first original model. On 30 May, Neuro-sama was announced to be participating in OffKai Expo 2023, held from 16–18 June. In June, she was averaging 5,700 viewers and in July she had over 300,000 Twitch followers; in a June interview with Bloomberg News, Vedal said that running Neuro-sama was his full-time job. By November, Neuro-sama had maintained her popularity and was averaging approximately 5,000 viewers; this was unlike most other types of AI-based entertainment which debuted at around the same time and garnered popularity before turning out to be "overhyped flops". On 16 December, Vedal won the Best Tech VTuber award at the 2023 VTuber Awards. On 19 December, Vedal began a subathon to coincide with Neuro-sama's first anniversary of streaming on Twitch (her "birthday"). The subathon ended on 4 January 2024. On 20 July 2024, Neuro-sama began streaming with Japanese subtitles on

  Read more →
• 

  NetMiner

  NetMiner is an all-in-one software platform for analyzing and visualizing complex network data, based on Social Network Analysis (SNA). Originally released in 2001, it supports research and education in a wide range of domains through interactive and visual data exploration. This tool allows researchers to explore their network data visually and interactively, and helps them to detect underlying patterns and structures of the network. It has also been recognized for its comprehensive features and user-friendly interface in comparative reviews of SNA software packages. == Features == === Integrated Data Environment === NetMiner supports unified management of diverse data types—including network (nodes and links), tabular, and unstructured text data—within a single platform. This enables users to perform the entire analysis workflow seamlessly without switching between tools. NetMiner also supports a wide range of analytical methods, allowing users to derive new insights by combining multiple approaches. Analytical results can be saved and reused across workflows(Add to Dataset) Graph and Network Analysis: Includes Centrality, Community Detection, Blockmodeling, and Similarity Measures. Machine learning: Provides algorithms for regression, classification, clustering, ensemble modeling and XAI(Explainable AI) Graph Neural Networks (GNNs): Supports models such as GraphSAGE, GCN, and GAT to learn from both node attributes and graph structure. Natural language processing (NLP): Uses pretrained deep learning models to analyze unstructured text, including named entity recognition and keyword extraction. Text mining and Text network analysis: Supports construction of word co-occurrence networks and topic modeling using LDA, BERTopic, enabling identification of thematic patterns and semantic structures in text data. Data Visualization: Offers advanced network visualization features, supporting multiple layout algorithms. Analytical outcomes such as centrality or community detection can be directly reflected in the network map via node size, color, and position, enhancing intuitive understanding. === AI Assistant === NetMiner integrates with external large language models such as OpenAI GPT and Google Gemini to interpret complex analysis results in natural language, summarize key findings, and suggest next steps for exploration. === Workflow and Usability === Designed to follow the structure of real-world data analysis workflows, NetMiner adopts a hierarchical data organization (Project → Workspace → Dataset → Data Item). Its web-based user interface improves clarity and reduces complexity. NetMiner 5 supports Windows 10 or higher and macOS 11 or later with M1 chip. Both academic and commercial licenses are available. == Extension == NetMiner Extension is small program to extend the functionality of NetMiner. In other words, it enables you to customize NetMiner according to your needs. By adding ‘NetMiner Extension’, you can expand your research. === Web Data Collection === NetMiner allows users to collect data from services such as YouTube, OpenAlex, Springer, and KCI via Open APIs. Collected data is automatically preprocessed and transformed to fit NetMiner’s internal structure, requiring no additional coding or external tools. SNS Data Collector: It collects social media data from YouTube, which has a large number of social media users worldwide. Biblio Data Collector: It collects the bibliographic data from Springer, OpenAlex, and KCI essential for research trend analysis. == File formats == === NetMiner data file format === .NMF === Importable/exportable formats === Plain text data: .TXT, .CSV Microsoft Excel data: .XLS, .XLSX Unstructured text data: .TXT, .CSV, .XLS(X) ※ NetMiner 4 only NetMiner 2 data: .NTF UCINet data: .DL, .DAT Pajek data: .NET, .VEC, .CLU, .PER StOCNET data file: .DAT Graph Modelling Language data: .GML(importing only) Related software UCINET Pajek Gephi StoCNET == Data structure == === Hierarchy of NetMiner data structure === NetMiner 5 supports not only graph data composed of nodes and links, but also tabular and unstructured data without fixed schema or identifiers. This enables users to easily import a wide variety of raw and unstructured data suitable for machine learning applications. Within a single workspace, users can manage node sets, link sets, and structured/unstructured data simultaneously. Multiple graph layers under a node set can be organized in a tree structure, allowing for intuitive understanding of the data currently being analyzed. == Release history == The first version of NetMiner was released on Dec 21, 2001. There have been five major updates from 2001. === NetMiner 5 === Released on June 9, 2025. NetMiner 5 retains the core features and no-code concept of NetMiner 4, but has evolved by integrating cutting-edge AI technologies. AI Assistant, Personal Analytics Tutor Support for Graph, Structured, and Unstructured Data Graph Analytics / Social Network Analysis Machine Learning(M/L) & XAI Graph Machine Learning(GML): Graph Neural Network Text Mining: Natural Language Processing(NLP), Text Network, Topic Modeling Data Visualization === NetMiner 4 (2011) === Latest version is 4.5.1. Introduced Python scripting, encrypted NMF format, semantic analysis tools (word cloud, topic modeling), and Extension - Data Collector. === NetMiner 3 (2007) === Enhanced scalability, integrated analysis-visualization modules, and DB import from Oracle, MS SQL. === NetMiner 2 (2003) === Improved statistical and network measures, visualization algorithms, and external data import modules.

  Read more →
• 

  Transderivational search

  Transderivational search (often abbreviated to TDS) is a psychological and cybernetics term, meaning when a search is being conducted for a fuzzy match across a broad field. In computing the equivalent function can be performed using content-addressable memory. Unlike usual searches, which look for literal (i.e. exact, logical, or regular expression) matches, a transderivational search is a search for a possible meaning or possible match as part of communication, and without which an incoming communication cannot be made any sense of whatsoever. It is thus an integral part of processing language, and of attaching meaning to communication. In NLP (Neuro-linguistic programming), a transderivational search (Bandler and Grinder, 1976) is essentially the process of searching back through one's stored memories and mental representations to find the personal reference experiences from which a current understanding or mental map has been derived. By the end of 1976, Grinder and Bandler had combined Satir’s and Perls’ language patterns and Erickson’s hypnotic language and use of metaphor with anchoring to create new processes that they called collapsing anchors, trans-derivational search, changing personal history, and reframing. A psychological example of TDS is in Ericksonian hypnotherapy, where vague suggestions are used that the patient must process intensely in order to find their own meanings, thus ensuring that the practitioner does not intrude his own beliefs into the subject's inner world. == TDS in human communication and processing == Because TDS is a compelling, automatic and unconscious state of internal focus and processing (i.e. a type of everyday trance state), and often a state of internal lack of certainty, or openness to finding an answer (since something is being checked out at that moment), it can be utilized or interrupted, in order to create, or deepen, trance. TDS is a fundamental part of human language and cognitive processing. Arguably, every word or utterance a person hears, for example, and everything they see or feel and take note of, results in a very brief trance while TDS is carried out to establish a contextual meaning for it. === Examples === Leading statements: "And those thoughts you had yesterday..." the human mind cannot process hearing this phrase, without at some level searching internally for some thoughts or other that it had yesterday, to make the subject of the sentence. "The many colors that fruit can be" likewise starts the human mind considering even if briefly, different fruit sorted by color. "You did it again, didn't you!" This everyday manipulative use of TDS usually sends the recipient looking internally for some "it" they may have done for which blame is being fairly given. Regardless of whether such a matter can be identified, guilt or anger may result. "There has been pain, hasn't there" the mind of a patient suffering an illness will find it very hard or impossible to hear or answer this sentence without conducting internal searches to verify whether this is true or not, or to find an example if so. "You'd forgotten something [or: some part of your body], hadn't you?" the mind usually checks through the various things, or parts of the body, on hearing this, seeing if each in turn has been forgotten. Textual ambiguity: "Do you remember line dancing on the steps?" Without sufficient context, some statements may trigger TDS in order to resolve inherent ambiguity in the interpretation of a posed question. Do I remember a bygone fad called "line dancing on the steps"? Do I remember personally engaging in dancing in the past? Do I remember my routine practice dancing by focusing on the steps of the dance? Do I tend to forget about dancing when I am standing on steps? "Penny-wise and pound the table dance to the beat of a different drummer". The mixing of cliché and stock phrases may trigger TDS in order to reconcile the discrepancies between expected and actual utterances in sequence. Although TDS is often associated with spoken language, it can be induced in any perceptual system. Thus Milton Erickson's "hypnotic handshake" is a technique that leaves the other person performing TDS in search of meaning to a deliberately ambiguous use of touch.

  Read more →
• 

  Contextual image classification

  Contextual image classification, a topic of pattern recognition in computer vision, is an approach of classification based on contextual information in images. "Contextual" means this approach is focusing on the relationship of the nearby pixels, which is also called neighbourhood. The goal of this approach is to classify the images by using the contextual information. == Introduction == Similar as processing language, a single word may have multiple meanings unless the context is provided, and the patterns within the sentences are the only informative segments we care about. For images, the principle is same. Find out the patterns and associate proper meanings to them. As the image illustrated below, if only a small portion of the image is shown, it is very difficult to tell what the image is about. Even try another portion of the image, it is still difficult to classify the image. However, if we increase the contextual of the image, then it makes more sense to recognize. As the full images shows below, almost everyone can classify it easily. During the procedure of segmentation, the methods which do not use the contextual information are sensitive to noise and variations, thus the result of segmentation will contain a great deal of misclassified regions, and often these regions are small (e.g., one pixel). Compared to other techniques, this approach is robust to noise and substantial variations for it takes the continuity of the segments into account. Several methods of this approach will be described below. == Applications == === Functioning as a post-processing filter to a labelled image === This approach is very effective against small regions caused by noise. And these small regions are usually formed by few pixels or one pixel. The most probable label is assigned to these regions. However, there is a drawback of this method. The small regions also can be formed by correct regions rather than noise, and in this case the method is actually making the classification worse. This approach is widely used in remote sensing applications. === Improving the post-processing classification === This is a two-stage classification process: For each pixel, label the pixel and form a new feature vector for it. Use the new feature vector and combine the contextual information to assign the final label to the === Merging the pixels in earlier stages === Instead of using single pixels, the neighbour pixels can be merged into homogeneous regions benefiting from contextual information. And provide these regions to classifier. === Acquiring pixel feature from neighbourhood === The original spectral data can be enriched by adding the contextual information carried by the neighbour pixels, or even replaced in some occasions. This kind of pre-processing methods are widely used in textured image recognition. The typical approaches include mean values, variances, texture description, etc. === Combining spectral and spatial information === The classifier uses the grey level and pixel neighbourhood (contextual information) to assign labels to pixels. In such case the information is a combination of spectral and spatial information. === Powered by the Bayes minimum error classifier === Contextual classification of image data is based on the Bayes minimum error classifier (also known as a naive Bayes classifier). Present the pixel: A pixel is denoted as x 0 {\displaystyle x_{0}} . The neighbourhood of each pixel x 0 {\displaystyle x_{0}} is a vector and denoted as N ( x 0 ) {\displaystyle N(x_{0})} . The values in the neighbourhood vector is denoted as f ( x i ) {\displaystyle f(x_{i})} . Each pixel is presented by the vector ξ = ( f ( x 0 ) , f ( x 1 ) , … , f ( x k ) ) {\displaystyle \xi =\left(f(x_{0}),f(x_{1}),\ldots ,f(x_{k})\right)} x i ∈ N ( x 0 ) ; i = 1 , … , k {\displaystyle x_{i}\in N(x_{0});\quad i=1,\ldots ,k} The labels (classification) of pixels in the neighbourhood N ( x 0 ) {\displaystyle N(x_{0})} are presented as a vector η = ( θ 0 , θ 1 , … , θ k ) {\displaystyle \eta =\left(\theta _{0},\theta _{1},\ldots ,\theta _{k}\right)} θ i ∈ { ω 0 , ω 1 , … , ω k } {\displaystyle \theta _{i}\in \left\{\omega _{0},\omega _{1},\ldots ,\omega _{k}\right\}} ω s {\displaystyle \omega _{s}} here denotes the assigned class. A vector presents the labels in the neighbourhood N ( x 0 ) {\displaystyle N(x_{0})} without the pixel x 0 {\displaystyle x_{0}} η ^ = ( θ 1 , θ 2 , … , θ k ) {\displaystyle {\hat {\eta }}=\left(\theta _{1},\theta _{2},\ldots ,\theta _{k}\right)} The neighbourhood: Size of the neighbourhood. There is no limitation of the size, but it is considered to be relatively small for each pixel x 0 {\displaystyle x_{0}} . A reasonable size of neighbourhood would be 3 × 3 {\displaystyle 3\times 3} of 4-connectivity or 8-connectivity ( x 0 {\displaystyle x_{0}} is marked as red and placed in the centre). The calculation: Apply the minimum error classification on a pixel x 0 {\displaystyle x_{0}} , if the probability of a class ω r {\displaystyle \omega _{r}} being presenting the pixel x 0 {\displaystyle x_{0}} is the highest among all, then assign ω r {\displaystyle \omega _{r}} as its class. θ 0 = ω r if P ( ω r ∣ f ( x 0 ) ) = max s = 1 , 2 , … , R P ( ω s ∣ f ( x 0 ) ) {\displaystyle \theta _{0}=\omega _{r}\quad {\text{ if }}\quad P(\omega _{r}\mid f(x_{0}))=\max _{s=1,2,\ldots ,R}P(\omega _{s}\mid f(x_{0}))} The contextual classification rule is described as below, it uses the feature vector x 1 {\displaystyle x_{1}} rather than x 0 {\displaystyle x_{0}} . θ 0 = ω r if P ( ω r ∣ ξ ) = max s = 1 , 2 , … , R P ( ω s ∣ ξ ) {\displaystyle \theta _{0}=\omega _{r}\quad {\text{ if }}\quad P(\omega _{r}\mid \xi )=\max _{s=1,2,\ldots ,R}P(\omega _{s}\mid \xi )} Use the Bayes formula to calculate the posteriori probability P ( ω s ∣ ξ ) {\displaystyle P(\omega _{s}\mid \xi )} P ( ω s ∣ ξ ) = p ( ξ ∣ ω s ) P ( ω s ) p ( ξ ) {\displaystyle P(\omega _{s}\mid \xi )={\frac {p(\xi \mid \omega _{s})P(\omega _{s})}{p\left(\xi \right)}}} The number of vectors is the same as the number of pixels in the image. For the classifier uses a vector corresponding to each pixel x i {\displaystyle x_{i}} , and the vector is generated from the pixel's neighbourhood. The basic steps of contextual image classification: Calculate the feature vector ξ {\displaystyle \xi } for each pixel. Calculate the parameters of probability distribution p ( ξ ∣ ω s ) {\displaystyle p(\xi \mid \omega _{s})} and P ( ω s ) {\displaystyle P(\omega _{s})} Calculate the posterior probabilities P ( ω r ∣ ξ ) {\displaystyle P(\omega _{r}\mid \xi )} and all labels θ 0 {\displaystyle \theta _{0}} . Get the image classification result. == Algorithms == === Template matching === The template matching is a "brute force" implementation of this approach. The concept is first create a set of templates, and then look for small parts in the image match with a template. This method is computationally high and inefficient. It keeps an entire templates list during the whole process and the number of combinations is extremely high. For a m × n {\displaystyle m\times n} pixel image, there could be a maximum of 2 m × n {\displaystyle 2^{m\times n}} combinations, which leads to high computation. This method is a top down method and often called table look-up or dictionary look-up. === Lower-order Markov chain === The Markov chain also can be applied in pattern recognition. The pixels in an image can be recognised as a set of random variables, then use the lower order Markov chain to find the relationship among the pixels. The image is treated as a virtual line, and the method uses conditional probability. === Hilbert space-filling curves === The Hilbert curve runs in a unique pattern through the whole image, it traverses every pixel without visiting any of them twice and keeps a continuous curve. It is fast and efficient. === Markov meshes === The lower-order Markov chain and Hilbert space-filling curves mentioned above are treating the image as a line structure. The Markov meshes however will take the two dimensional information into account. === Dependency tree === The dependency tree is a method using tree dependency to approximate probability distributions.

  Read more →
• 

  Human–robot interaction

  Human–robot interaction (HRI) is the study of interactions between humans and robots. Human–robot interaction is a multidisciplinary field with contributions from human–computer interaction, artificial intelligence, robotics, natural language processing, design, psychology and philosophy. A subfield known as physical human–robot interaction (pHRI) has tended to focus on device design to enable people to safely interact with robotic systems. == Origins == Human–robot interaction has been a topic of both science fiction and academic speculation even before any robots existed. Because much of active HRI development depends on natural language processing, many aspects of HRI are continuations of human communications, a field of research which is much older than robotics. The origin of HRI as a discrete problem was stated by 20th-century author Isaac Asimov in 1941, in his novel I, Robot. Asimov coined Three Laws of Robotics, namely: A robot may not injure a human being or, through inaction, allow a human being to come to harm. A robot must obey the orders given it by human beings except where such orders would conflict with the First Law. A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws. These three laws provide an overview of the goals engineers and researchers hold for safety in the HRI field, although the fields of robot ethics and machine ethics are more complex than these three principles. However, generally human–robot interaction prioritizes the safety of humans that interact with potentially dangerous robotics equipment. Solutions to this problem range from the philosophical approach of treating robots as ethical agents (individuals with moral agency), to the practical approach of creating safety zones. These safety zones use technologies such as lidar to detect human presence or physical barriers to protect humans by preventing any contact between machine and operator. Although initially robots in the human–robot interaction field required some human intervention to function, research has expanded this to the extent that fully autonomous systems are now far more common than in the early 2000s. Autonomous systems include from simultaneous localization and mapping systems which provide intelligent robot movement to natural-language processing and natural-language generation systems which allow for natural, human-esque interaction which meet well-defined psychological benchmarks. Anthropomorphic robots (machines which imitate human body structure) are better described by the biomimetics field, but overlap with HRI in many research applications. Examples of robots which demonstrate this trend include Willow Garage's PR2 robot, the NASA Robonaut, and Honda ASIMO. However, robots in the human–robot interaction field are not limited to human-like robots: Paro and Kismet are both robots designed to elicit emotional response from humans, and so fall into the category of human–robot interaction. Goals in HRI range from industrial manufacturing through Cobots, medical technology through rehabilitation, autism intervention, and elder care devices, entertainment, human augmentation, and human convenience. Future research therefore covers a wide range of fields, much of which focuses on assistive robotics, robot-assisted search-and-rescue, and space exploration. == The goal of friendly human–robot interactions == Robots are artificial agents with capacities of perception and action in the physical world often referred by researchers as workspace. Their use has been generalized in factories but nowadays they tend to be found in the most technologically advanced societies in such critical domains as search and rescue, military battle, mine and bomb detection, scientific exploration, law enforcement, entertainment and hospital care. These new domains of applications imply a closer interaction with the user, sharing the workspace but also goals in terms of task achievement. The subfield of physical human–robot interaction (pHRI) has largely focused on device design to enable people to safely interact with robotic systems but is increasingly developing algorithmic approaches in an attempt to support fluent and expressive interactions between humans and robotic systems. With the advance in AI, the research is focusing on one part towards the safest physical interaction but also on a socially correct interaction, dependent on cultural criteria. The goal is to build an intuitive, and easy communication with the robot through speech, gestures, and facial expressions. Kerstin Dautenhahn refers to friendly Human–robot interaction as "Robotiquette" defining it as the "social rules for robot behaviour (a 'robotiquette') that is comfortable and acceptable to humans" The robot has to adapt itself to our way of expressing desires and orders and not the contrary. But every day environments such as homes have much more complex social rules than those implied by factories or even military environments. Thus, the robot needs perceiving and understanding capacities to build dynamic models of its surroundings. It needs to categorize objects, recognize and locate humans and further recognize their emotions. The need for dynamic capacities pushes forward every sub-field of robotics. Furthermore, by understanding and perceiving social cues, robots can enable collaborative scenarios with humans. For example, with the rapid rise of personal fabrication machines such as desktop 3D printers, laser cutters, etc., entering our homes, scenarios may arise where robots can collaboratively share control, co-ordinate and achieve tasks together. Industrial robots have already been integrated into industrial assembly lines and are collaboratively working with humans. The social impact of such robots have been studied and has indicated that workers still treat robots and social entities, rely on social cues to understand and work together. On the other end of HRI research the cognitive modelling of the "relationship" between human and the robots benefits the psychologists and robotic researchers the user study are often of interests on both sides. This research endeavours part of human society. For effective human – humanoid robot interaction numerous communication skills and related features should be implemented in the design of such artificial agents/systems. == General HRI research == HRI research spans a wide range of fields, some general to the nature of HRI. === Methods for perceiving humans === Methods for perceiving humans in the environment are based on sensor information. Research on sensing components and software led by Microsoft provide useful results for extracting the human kinematics (see Kinect). An example of older technique is to use colour information for example the fact that for light skinned people the hands are lighter than the clothes worn. In any case a human modelled a priori can then be fitted to the sensor data. The robot builds or has (depending on the level of autonomy the robot has) a 3D mapping of its surroundings to which is assigned the humans locations. Most methods intend to build a 3D model through vision of the environment. The proprioception sensors permit the robot to have information over its own state. This information is relative to a reference. Theories of proxemics may be used to perceive and plan around a person's personal space. A speech recognition system is used to interpret human desires or commands. By combining the information inferred by proprioception, sensor and speech the human position and state (standing, seated). In this matter, natural-language processing is concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural-language data. For instance, neural-network architectures and learning algorithms that can be applied to various natural-language processing tasks including part-of-speech tagging, chunking, named-entity recognition, and semantic role labeling. === Methods for motion planning === Motion planning in dynamic environments is a challenge that can at the moment only be achieved for robots with 3 to 10 degrees of freedom. Humanoid robots or even 2 armed robots, which can have up to 40 degrees of freedom, are unsuited for dynamic environments with today's technology. However lower-dimensional robots can use the potential field method to compute trajectories which avoid collisions with humans. === Cognitive models and theory of mind === Humans exhibit negative social and emotional responses as well as decreased trust toward some robots that closely, but imperfectly, resemble humans; this phenomenon has been termed the "Uncanny Valley". However recent research in telepresence robots has established that mimicking human body postures and expressive gestures has made the robots likeable and engaging in a remote setting. Further, the presence o

  Read more →
• 

  Semantic space

  Semantic spaces in the natural language domain aim to create representations of natural language that are capable of capturing meaning. The original motivation for semantic spaces stems from two core challenges of natural language: Vocabulary mismatch (the fact that the same meaning can be expressed in many ways) and ambiguity of natural language (the fact that the same term can have several meanings). The application of semantic spaces in natural language processing (NLP) aims at overcoming limitations of rule-based or model-based approaches operating on the keyword level. The main drawback with these approaches is their brittleness, and the large manual effort required to create either rule-based NLP systems or training corpora for model learning. Rule-based and machine learning based models are fixed on the keyword level and break down if the vocabulary differs from that defined in the rules or from the training material used for the statistical models. Research in semantic spaces dates back more than 20 years. In 1996, two papers were published that raised a lot of attention around the general idea of creating semantic spaces: latent semantic analysis and Hyperspace Analogue to Language. However, their adoption was limited by the large computational effort required to construct and use those semantic spaces. A breakthrough with regard to the accuracy of modelling associative relations between words (e.g. "spider-web", "lighter-cigarette", as opposed to synonymous relations such as "whale-dolphin", "astronaut-driver") was achieved by explicit semantic analysis (ESA) in 2007. ESA was a novel (non-machine learning) based approach that represented words in the form of vectors with 100,000 dimensions (where each dimension represents an Article in Wikipedia). However practical applications of the approach are limited due to the large number of required dimensions in the vectors. More recently, advances in neural network techniques in combination with other new approaches (tensors) led to a host of new recent developments: Word2vec from Google, GloVe from Stanford University, and fastText from Facebook AI Research (FAIR) labs.

  Read more →
• 

  Neural processing unit

  A neural processing unit (NPU), also known as an AI accelerator or deep learning processor, is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence and machine learning applications, including artificial neural networks and computer vision. == Use == Their purpose is either to efficiently execute already trained AI models (inference) or to train AI models. NPUs can be more efficient in terms of speed or power consumption. NPU applications include algorithms for robotics, Internet of things, and data-intensive or sensor-driven tasks. They are often manycore or spatial designs and focus on low-precision arithmetic, novel dataflow architectures, or in-memory computing capability. As of 2024, a widely used datacenter-grade AI integrated circuit chip, the Nvidia H100 GPU, contains tens of billions of MOSFETs. === Consumer devices === AI accelerators are used in Apple silicon, Qualcomm, Samsung, Huawei, and Google Tensor smartphone processors. Vision processing units are accelerators specialized for machine vision algorithms such as CNN (convolutional neural networks) and SIFT (scale-invariant feature transform). They are used in devices that need to keep track of objects visually such as AR headsets and drones. It is more recently (circa 2017) added to processors from Apple and (circa 2022) to processors from Intel and AMD. All models of Intel Meteor Lake processors have a built-in versatile processor unit (VPU) for accelerating inference for computer vision and deep learning. On consumer devices, the NPU is intended to be small, power-efficient, but reasonably fast when used to run small models. To do this they are designed to support low-bitwidth operations using data types such as INT4, INT8, FP8, and FP16. A common metric is trillions of operations per second (TOPS). Although TOPS does not explicitly specify the kind of operations, it is typically INT8 additions and multiplications. === Datacenters === Accelerators are used in cloud computing servers: e.g., tensor processing units (TPU) for Google Cloud Platform, and Trainium and Inferentia chips for Amazon Web Services. Many vendor-specific terms exist for devices in this category, and it is an emerging technology without a dominant design. Since the late 2010s, graphics processing units designed by companies such as Nvidia and AMD often include AI-specific hardware in the form of dedicated functional units for low-precision matrix-multiplication operations. These GPUs are commonly used as AI accelerators, both for training and inference. === Scientific computation === Although NPUs are tailored for low-precision (e.g., FP16, INT8) matrix multiplication operations, they can be used to emulate higher-precision matrix multiplications in scientific computing. As modern GPUs place much focus on making the NPU part fast, using emulated FP64 (Ozaki scheme) on NPUs can potentially outperform native FP64. This has been demonstrated using FP16-emulated FP64 on NVIDIA TITAN RTX and using INT8-emulated FP64 on NVIDIA consumer GPUs and the A100 GPU. Consumer GPUs especially benefited as they have limited FP64 hardware capacity, showing a 6× speedup. Since CUDA Toolkit 13.0 Update 2, cuBLAS automatically uses INT8-emulated FP64 matrix multiplication of the equivalent precision if it is faster than native. This is in addition to the FP16-emulated FP32 feature introduced in version 12.9. == Programming == An operating system or a higher-level library may provide application programming interfaces such as TensorFlow with LiteRT Next (Android), CoreML (iOS, macOS) or DirectML (Windows). Formats such as ONNX are used to represent trained neural networks. Consumer CPU-integrated NPUs are accessible through vendor-specific APIs. AMD (Ryzen AI), Intel (OpenVINO), Apple silicon (CoreML), and Qualcomm (SNPE) each have their own APIs, which can be built upon by a higher-level library. GPUs generally use existing GPGPU pipelines such as CUDA and OpenCL adapted for lower precisions and specialized matrix-multiplication operations. Vulkan is also being used. Custom-built systems such as the Google TPU use private interfaces. There are a large number of separate underlying acceleration APIs and compilers/runtimes in use in the AI field, causing a great increase in software development effort due to the many combinations involved. As of 2025, the open standard organization Khronos Group is pursuing standardization of AI-related interfaces to reduce the amount of work needed. Khronos is working on three separate fronts: expansion of data types and intrinsic operations in OpenCL and Vulkan, inclusion of compute graphs in SPIR-V, and a NNEF/SkriptND file format for describing a neural network.

  Read more →
• 

  Xiaomi MiMo

  Xiaomi MiMo is a family of large language models (LLMs) developed by Xiaomi. It was initially released in April 2025 with the MiMo-7B model. Currently, MiMo is available for developers through API service. It is used as the key AI model in Xiaomi's "Human x Car x Home" ecosystem. == Development == Xiaomi developed MiMo as a reasoning-focused language model. Its development team was led by Luo Fuli, who had previously worked at DeepSeek before joining Xiaomi in late 2025. The model was trained using multi-token prediction and reinforcement learning, with a particular emphasis on mathematical reasoning and code generation tasks. In March 2026, Xiaomi CEO Lei Jun announced that the company planned to invest at least US$8.7 billion in artificial intelligence over the following three years. == Models == === List of models === === MiMo-7B === MiMo-7B is the first model of this LLM. The base model, MiMo-7B-Base, was pre-trained on approximately 25 trillion tokens using web pages, academic papers, books, and synthetic reasoning data. MiMo-7B-RL underwent supervised fine-tuning and reinforcement learning on 130,000 mathematics and code problems. MiMo-7B-RL-0530 was released in May 2025. It scaled the fine-tuning dataset from 500,000 to 6 million instances and extended the RL window from 32,000 to 48,000 tokens and improved AIME 2024 scores from 68.2 to 80.1. MiMo-VL-7B was a vision-language model combining a Vision Transformer encoder with the MiMo-7B backbone. It was trained in four stages consuming 2.4 trillion tokens. Its reinforcement learning variant used Mixed On-Policy Reinforcement Learning (MORL) which integrated reward signals across perception, grounding, and reasoning. Xiaomi also released MiMo-Audio-7B, an audio-language model for voice conversion, style transfer, and speech editing. === MiMo-V2-Flash === MiMo-V2-Flash was launched in December 2025. It is a open-sourced Mixture-of-experts model with 309 billion total parameters and 15 billion active parameters. It was trained on 27 trillion tokens using FP8 mixed precision. It used hybrid attention interleaving Sliding Window and Global Attention at a 5:1 ratio. === MiMo-V2-Pro === Xiaomi publicly introduced MiMo-V2-Pro on 18 March 2026. It has over 1 trillion total parameters, 42 billion active, and a 1-million-token context window. Before the official release, the model had appeared anonymously on OpenRouter under the codename "Hunter Alpha," where it drew substantial usage and topped daily charts for several days, according to Xiaomi and Reuters. During its listing on OpenRouter, the model reportedly processed over one trillion tokens in total usage. Xiaomi later said Hunter Alpha was an early internal test build of MiMo-V2-Pro, and Reuters reported that the model had been mistaken by some users for a possible DeepSeek system before Xiaomi confirmed its origin. The model was released as a proprietary API product, and Luo Fuli stated that Xiaomi intended to open-source a variant at an unspecified future date. Xiaomi has partnered with several API web platforms like OpenClaw to launch the model. All these websites initially offered a free trial of this model for a week, but due to the overwhelming response, Xiaomi later extended the free trial period of the model until 2 April 2026. === MiMo-V2-Omni === Alongside MiMo-V2-Pro, Xiaomi launched MiMo-V2-Omni on 18 March 2026. It handles image, video, audio, and text inputs. Before the official release, it was codenamed "Healer Alpha" in OpenRouter. === MiMo-V2-TTS === On the same date as the release of MiMo-V2-Pro and MiMo-V2-Omni, a Text-to-Speech model named MiMo-V2-TTS was released also. It is a speech synthesis model. It was trained on audio data, which makes it capable of emotional transitions, mid-sentence tone shifts, singing, and synthesis of regional dialects like Sichuan, Cantonese, Henan, and Taiwanese. == Licensing == Xiaomi has used different licensing approaches for different models in the MiMo family. The MiMo-7B series and MiMo-V2-Flash were released as open-weight models. MiMo-V2-Flash was published under the MIT license with model weights and inference code available on Hugging Face. MiMo-V2-Pro and MiMo-V2-Omni were released as proprietary models. It was accessible through Xiaomi's API platform and third-party API providers. Luo Fuli stated that Xiaomi intended to open-source a variant of MiMo-V2-Pro. Although, she did not specify any timeline. MiMo-V2-TTS was released as a proprietary model with no publicly available weights.

  Read more →
• 

  Neurorobotics

  Neurorobotics is the combined study of neuroscience, robotics, and artificial intelligence. It is the science and technology of embodied autonomous neural systems. Neural systems include brain-inspired algorithms (e.g. connectionist networks), computational models of biological neural networks (e.g. artificial spiking neural networks, large-scale simulations of neural microcircuits) and actual biological systems (e.g. in vivo and in vitro neural nets). Such neural systems can be embodied in machines with mechanic or any other forms of physical actuation. This includes robots, prosthetic or wearable systems but also, at smaller scale, micro-machines and, at the larger scales, furniture and infrastructures. Neurorobotics is that branch of neuroscience with robotics, which deals with the study and application of science and technology of embodied autonomous neural systems like brain-inspired algorithms. It is based on the idea that the brain is embodied and the body is embedded in the environment. Therefore, most neurorobots are required to function in the real world, as opposed to a simulated environment. Beyond brain-inspired algorithms for robots neurorobotics may also involve the design of brain-controlled robot systems. == Major classes of models == Neurorobots can be divided into various major classes based on the robot's purpose. Each class is designed to implement a specific mechanism of interest for study. Common types of neurorobots are those used to study motor control, memory, action selection, and perception. === Locomotion and motor control === Neurorobots are often used to study motor feedback and control systems, and have proved their merit in developing controllers for robots. Locomotion is modeled by a number of neurologically inspired theories on the action of motor systems. Locomotion control has been mimicked using models or central pattern generators, clumps of neurons capable of driving repetitive behavior, to make four-legged walking robots. Other groups have expanded the idea of combining rudimentary control systems into a hierarchical set of simple autonomous systems. These systems can formulate complex movements from a combination of these rudimentary subsets. This theory of motor action is based on the organization of cortical columns, which progressively integrate from simple sensory input into a complex afferent signals, or from complex motor programs to simple controls for each muscle fiber in efferent signals, forming a similar hierarchical structure. Another method for motor control uses learned error correction and predictive controls to form a sort of simulated muscle memory. In this model, awkward, random, and error-prone movements are corrected for using error feedback to produce smooth and accurate movements over time. The controller learns to create the correct control signal by predicting the error. Using these ideas, robots have been designed which can learn to produce adaptive arm movements or to avoid obstacles in a course. === Learning and memory systems === Robots designed to test theories of animal memory systems. Many studies examine the memory system of rats, particularly the rat hippocampus, dealing with place cells, which fire for a specific location that has been learned. Systems modeled after the rat hippocampus are generally able to learn mental maps of the environment, including recognizing landmarks and associating behaviors with them, allowing them to predict the upcoming obstacles and landmarks. Another study has produced a robot based on the proposed learning paradigm of barn owls for orientation and localization based on primarily auditory, but also visual stimuli. The hypothesized method involves synaptic plasticity and neuromodulation, a mostly chemical effect in which reward neurotransmitters such as dopamine or serotonin affect the firing sensitivity of a neuron to be sharper. The robot used in the study adequately matched the behavior of barn owls. Furthermore, the close interaction between motor output and auditory feedback proved to be vital in the learning process, supporting active sensing theories that are involved in many of the learning models. Neurorobots in these studies are presented with simple mazes or patterns to learn. Some of the problems presented to the neurorobot include recognition of symbols, colors, or other patterns and execute simple actions based on the pattern. In the case of the barn owl simulation, the robot had to determine its location and direction to navigate in its environment. === Action selection and value systems === Action selection studies deal with negative or positive weighting to an action and its outcome. Neurorobots can and have been used to study simple ethical interactions, such as the classical thought experiment where there are more people than a life raft can hold, and someone must leave the boat to save the rest. However, more neurorobots used in the study of action selection contend with much simpler persuasions such as self-preservation or perpetuation of the population of robots in the study. These neurorobots are modeled after the neuromodulation of synapses to encourage circuits with positive results. In biological systems, neurotransmitters such as dopamine or acetylcholine positively reinforce neural signals that are beneficial. One study of such interaction involved the robot Darwin VII, which used visual, auditory, and a simulated taste input to "eat" conductive metal blocks. The arbitrarily chosen good blocks had a striped pattern on them while the bad blocks had a circular shape on them. The taste sense was simulated by conductivity of the blocks. The robot had positive and negative feedbacks to the taste based on its level of conductivity. The researchers observed the robot to see how it learned its action selection behaviors based on the inputs it had. Other studies have used herds of small robots which feed on batteries strewn about the room, and communicate its findings to other robots. === Sensory perception === Neurorobots have also been used to study sensory perception, particularly vision. These are primarily systems that result from embedding neural models of sensory pathways in automatas. This approach gives exposure to the sensory signals that occur during behavior and also enables a more realistic assessment of the degree of robustness of the neural model. It is well known that changes in the sensory signals produced by motor activity provide useful perceptual cues that are used extensively by organisms. For example, researchers have used the depth information that emerges during replication of human head and eye movements to establish robust representations of the visual scene. == Biological robots == Biological robots are not officially neurorobots in that they are not neurologically inspired AI systems, but actual neuron tissue wired to a robot. This employs the use of cultured neural networks to study brain development or neural interactions. These typically consist of a neural culture raised on a multielectrode array (MEA), which is capable of both recording the neural activity and stimulating the tissue. In some cases, the MEA is connected to a computer which presents a simulated environment to the brain tissue and translates brain activity into actions in the simulation, as well as providing sensory feedback The ability to record neural activity gives researchers a window into a brain, which they can use to learn about a number of the same issues neurorobots are used for. An area of concern with the biological robots is ethics. Many questions are raised about how to treat such experiments. The central question concerns consciousness and whether or not the rat brain experiences it. There are many theories about how to define consciousness. == Implications for neuroscience == Neuroscientists benefit from neurorobotics because it provides a blank slate to test various possible methods of brain function in a controlled and testable environment. While robots are more simplified versions of the systems they emulate, they are more specific, allowing more direct testing of the issue at hand. They also have the benefit of being accessible at all times, while it is more difficult to monitor large portions of a brain while the human or animal is active, especially individual neurons. The development of neuroscience has produced neural treatments. These include pharmaceuticals and neural rehabilitation. Progress is dependent on an intricate understanding of the brain and how exactly it functions. It is difficult to study the brain, especially in humans, due to the danger associated with cranial surgeries. Neurorobots can improved the range of tests and experiments that can be performed in the study of neural processes.

  Read more →
• 

  SPL notation

  SPL (Sentence Plan Language) is an abstract notation representing the semantics of a sentence in natural language. In a classical Natural Language Generation (NLG) workflow, an initial text plan (hierarchically or sequentially organized factoids, often modelled in accordance with Rhetorical Structure Theory) is transformed by a sentence planner (generator) component to a sequence of sentence plans modelled in a Sentence Plan Language. A surface generator can be used to transform the SPL notation into natural language sentences. Probably the most widely used SPL language used today (2022) is AMR (Abstract Meaning Representation, see there for further references), but is owes parts of its popularity to its application to NLP problems other than NLG, e.g., machine translation and semantic parsing.

  Read more →
• 

  Seq2seq

  Seq2seq is a family of machine learning approaches used for natural language processing. Originally developed by Lê Viết Quốc, a Vietnamese computer scientist and a machine learning pioneer at Google Brain, this framework has become foundational in many modern AI systems. Applications include language translation, image captioning, conversational models, speech recognition, and text summarization. Seq2seq uses sequence transformation: it turns one sequence into another sequence. == History == One naturally wonders if the problem of translation could conceivably be treated as a problem in cryptography. When I look at an article in Russian, I say: 'This is really written in English, but it has been coded in some strange symbols. I will now proceed to decode. seq2seq is an approach to machine translation (or more generally, sequence transduction) with roots in information theory, where communication is understood as an encode-transmit-decode process, and machine translation can be studied as a special case of communication. This viewpoint was elaborated, for example, in the noisy channel model of machine translation. In practice, seq2seq maps an input sequence into a real-numerical vector by using a neural network (the encoder), and then maps it back to an output sequence using another neural network (the decoder). The idea of encoder-decoder sequence transduction had been developed in the early 2010s. The papers most commonly cited as the originators that produced seq2seq are two papers from 2014. In the seq2seq as proposed by them, both the encoder and the decoder were LSTMs. This had the "bottleneck" problem, since the encoding vector has a fixed size, so for long input sequences, information would tend to be lost, as they are difficult to fit into the fixed-length encoding vector. The attention mechanism, proposed in 2014, resolved the bottleneck problem. They called their model RNNsearch, as it "emulates searching through a source sentence during decoding a translation". A problem with seq2seq models at this point was that recurrent neural networks are difficult to parallelize. The 2017 publication of Transformers resolved the problem by replacing the encoding RNN with self-attention Transformer blocks ("encoder blocks"), and the decoding RNN with cross-attention causally-masked Transformer blocks ("decoder blocks"). === Priority dispute === One of the papers cited as the originator for seq2seq is (Sutskever et al 2014), published at Google Brain while they were on Google's machine translation project. The research allowed Google to overhaul Google Translate into Google Neural Machine Translation in 2016. Tomáš Mikolov claims to have developed the idea (before joining Google Brain) of using a "neural language model on pairs of sentences... and then [generating] translation after seeing the first sentence"—which he equates with seq2seq machine translation, and to have mentioned the idea to Ilya Sutskever and Quoc Le (while at Google Brain), who failed to acknowledge him in their paper. Mikolov had worked on RNNLM (using RNN for language modelling) for his PhD thesis, and is more notable for developing word2vec. == Architecture == The main reference for this section is. === Encoder === The encoder is responsible for processing the input sequence and capturing its essential information, which is stored as the hidden state of the network and, in a model with attention mechanism, a context vector. The context vector is the weighted sum of the input hidden states and is generated for every time instance in the output sequences. === Decoder === The decoder takes the context vector and hidden states from the encoder and generates the final output sequence. The decoder operates in an autoregressive manner, producing one element of the output sequence at a time. At each step, it considers the previously generated elements, the context vector, and the input sequence information to make predictions for the next element in the output sequence. Specifically, in a model with attention mechanism, the context vector and the hidden state are concatenated together to form an attention hidden vector, which is used as an input for the decoder. The seq2seq method developed in the early 2010s uses two neural networks: an encoder network converts an input sentence into numerical vectors, and a decoder network converts those vectors to sentences in the target language. The Attention mechanism was grafted onto this structure in 2014 and is shown below. Later it was refined into the encoder-decoder Transformer architecture of 2017. === Training vs prediction === There is a subtle difference between training and prediction. During training time, both the input and the output sequences are known. During prediction time, only the input sequence is known, and the output sequence must be decoded by the network itself. Specifically, consider an input sequence x 1 : n {\displaystyle x_{1:n}} and output sequence y 1 : m {\displaystyle y_{1:m}} . The encoder would process the input x 1 : n {\displaystyle x_{1:n}} step by step. After that, the decoder would take the output from the encoder, as well as the as input, and produce a prediction y ^ 1 {\displaystyle {\hat {y}}_{1}} . Now, the question is: what should be input to the decoder in the next step? A standard method for training is "teacher forcing". In teacher forcing, no matter what is output by the decoder, the next input to the decoder is always the reference. That is, even if y ^ 1 ≠ y 1 {\displaystyle {\hat {y}}_{1}\neq y_{1}} , the next input to the decoder is still y 1 {\displaystyle y_{1}} , and so on. During prediction time, the "teacher" y 1 : m {\displaystyle y_{1:m}} would be unavailable. Therefore, the input to the decoder must be y ^ 1 {\displaystyle {\hat {y}}_{1}} , then y ^ 2 {\displaystyle {\hat {y}}_{2}} , and so on. It is found that if a model is trained purely by teacher forcing, its performance would degrade during prediction time, since generation based on the model's own output is different from generation based on the teacher's output. This is called exposure bias or a train/test distribution shift. A 2015 paper recommends that, during training, randomly switch between teacher forcing and no teacher forcing. === Attention for seq2seq === The attention mechanism is an enhancement introduced by Bahdanau et al. in 2014 to address limitations in the basic Seq2Seq architecture where a longer input sequence results in the hidden state output of the encoder becoming irrelevant for the decoder. It enables the model to selectively focus on different parts of the input sequence during the decoding process. At each decoder step, an alignment model calculates the attention score using the current decoder state and all of the attention hidden vectors as input. An alignment model is another neural network model that is trained jointly with the seq2seq model used to calculate how well an input, represented by the hidden state, matches with the previous output, represented by attention hidden state. A softmax function is then applied to the attention score to get the attention weight. In some models, the encoder states are directly fed into an activation function, removing the need for alignment model. An activation function receives one decoder state and one encoder state and returns a scalar value of their relevance. Consider the seq2seq language English-to-French translation task. To be concrete, let us consider the translation of "the zone of international control ", which should translate to "la zone de contrôle international ". Here, we use the special token as a control character to delimit the end of input for both the encoder and the decoder. An input sequence of text x 0 , x 1 , … {\displaystyle x_{0},x_{1},\dots } is processed by a neural network (which can be an LSTM, a Transformer encoder, or some other network) into a sequence of real-valued vectors h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , where h {\displaystyle h} stands for "hidden vector". After the encoder has finished processing, the decoder starts operating over the hidden vectors, to produce an output sequence y 0 , y 1 , … {\displaystyle y_{0},y_{1},\dots } , autoregressively. That is, it always takes as input both the hidden vectors produced by the encoder, and what the decoder itself has produced before, to produce the next output word: ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , "") → "la" ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la") → "la zone" ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la zone") → "la zone de" ... ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la zone de contrôle international") → "la zone de contrôle international " Here, we use the special token as a control character to delimit the start of input for the decoder. The decoding terminates as soon as "" appears in the decoder output. ==

  Read more →
• 

  Photo-consistency

  In computer vision, photo-consistency determines whether a given voxel is occupied. A voxel is considered to be photo consistent when its color appears to be similar to all the cameras that can see it. Most voxel coloring or space carving techniques require using photo consistency as a check condition in Image-based modeling and rendering applications. == Usage == 3D Volumetric Reconstruction. Image registration. Multi-view reconstruction.

  Read more →
• 

  Commission on Enhancing National Cybersecurity

  The President's Commission on Enhancing National Cybersecurity is a Presidential Commission formed on April 13, 2016, to develop a plan for protecting cyberspace, and America's economic reliance on it. The commission released its final report in December 2016. The report made recommendations regarding the intertwining roles of the military, government administration and the private sector in providing cyber security. Chairman Donilon said of the report that its coverage "is unusual in the breadth of issues" with which it deals. == Recommendations == The report made sixteen major recommendations with fifty-three specific action items broadly grouped under six areas: Protecting the information and digital infrastructure Investing in the secure growth of information and digital infrastructure Consumer information access Building the cybersecurity workforce Building a secure governmental cybersecurity framework Keeping interconnectivity open, fair, competitive, and secure The Commission found that strong authentication systems were mandatory for adequate cybersecurity, not just for the government, but for all commercial systems, and private individuals. The commission also stressed remote identity proofing and security for the Internet of things (IoT). Finding that technicians who know cybersecurity and can protect systems are few and in short supply, the commission recommended nationally supported training programs to produce an adequate workforce, as well as increasing the level of expertise in the existing workforce. The Commission highlighted the importance of partnerships between government and the private sector as a powerful tool for encouraging the technology, policies and practices we need to secure and grow the digital economy. (page 2) Some criticised the commission's work as lacking an understanding of cybersecurity and not being cognizant of "cyber reality" and the cost of some of the action items, but others found the report constructive and meaningful. == Commission members == The initial members of the Commission are: Tom Donilon, former Assistant to the President and National Security Advisor (Chair) Sam Palmisano, former CEO of IBM (Vice Chair) General Keith Alexander, CEO of IronNet Cybersecurity, former Director of the National Security Agency and former Commander of U.S. Cyber Command Annie Antón, Professor and Chair of the School of Interactive Computing at Georgia Tech. Ajay Banga, President and CEO of MasterCard Steven Chabinsky, General Counsel and Chief Risk Officer of CrowdStrike Patrick Gallagher, Chancellor of the University of Pittsburgh and former Director of the National Institute of Standards and Technology Peter Lee, Corporate Vice President, Microsoft Research Herbert Lin, Senior Research Scholar for Cyber Policy and Security at the Stanford Center for International Security and Cooperation and Research Fellow at the Hoover Institution Heather Murren, former member of the Financial Crisis Inquiry Commission and co-founder of the Nevada Cancer Institute Joe Sullivan, Chief Security Officer of Uber and former Chief Security Officer of Facebook Maggie Wilderotter, Executive Chairman of Frontier Communications == Follow-on == Incoming President Trump has indicated that he wants a full review of U.S. cyber protection policy. == Notes and references ==

  Read more →
• 

  CMU Pronouncing Dictionary

  The CMU Pronouncing Dictionary (also known as CMUdict) is an open-source pronouncing dictionary originally created by the Speech Group at Carnegie Mellon University (CMU) for use in speech recognition research. CMUdict provides a mapping orthographic/phonetic for English words in their North American pronunciations. It is commonly used to generate representations for speech recognition (ASR), e.g. the CMU Sphinx system, and speech synthesis (TTS), e.g. the Festival system. CMUdict can be used as a training corpus for building statistical grapheme-to-phoneme (g2p) models that will generate pronunciations for words not yet included in the dictionary. The most recent release is 0.7b; it contains over 134,000 entries. An interactive lookup version is available. == Database format == The database is distributed as a plain text file with one entry to a line in the format "WORD " with a two-space separator between the parts. If multiple pronunciations are available for a word, variants are identified using numbered versions (e.g. WORD(1)). The pronunciation is encoded using a modified form of the ARPABET system, with the addition of stress marks on vowels of levels 0, 1, and 2. A line-initial ;;; token indicates a comment. A derived format, directly suitable for speech recognition engines is also available as part of the distribution; this format collapses stress distinctions (typically not used in ASR). The following is a table of phonemes used by CMU Pronouncing Dictionary. == History == == Applications == The Unifon converter is based on the CMU Pronouncing Dictionary. The Natural Language Toolkit contains an interface to the CMU Pronouncing Dictionary. The Carnegie Mellon Logios tool incorporates the CMU Pronouncing Dictionary. PronunDict, a pronunciation dictionary of American English, uses the CMU Pronouncing Dictionary as its data source. Pronunciation is transcribed in IPA symbols. This dictionary also supports searching by pronunciation. Some singing voice synthesizer software like CeVIO Creative Studio and Synthesizer V uses modified version of CMU Pronouncing Dictionary for synthesizing English singing voices. Transcriber, a tool for the full text phonetic transcription, uses the CMU Pronouncing Dictionary 15.ai, a real-time text-to-speech tool using artificial intelligence, uses the CMU Pronouncing Dictionary

  Read more →
• 

  Attempto Controlled English

  Attempto Controlled English (ACE) is a controlled natural language, i.e. a subset of standard English with a restricted syntax and restricted semantics described by a small set of construction and interpretation rules. It has been under development at the University of Zurich since 1995. In 2013, ACE version 6.7 was announced. ACE can serve as knowledge representation, specification, and query language, and is intended for professionals who want to use formal notations and formal methods, but may not be familiar with them. Though ACE appears perfectly natural—it can be read and understood by any speaker of English—it is in fact a formal language. ACE and its related tools have been used in the fields of software specifications, theorem proving, proof assistants, text summaries, ontologies, rules, querying, medical documentation and planning. Here are some simple examples: Every woman is a human. A woman is a human. A man tries-on a new tie. If the tie pleases his wife then the man buys it. ACE construction rules require that each noun be introduced by a determiner (a, every, no, some, at least 5, ...). Regarding the list of examples above, ACE interpretation rules decide that (1) is interpreted as universally quantified, while (2) is interpreted as existentially quantified. Sentences like "Women are human" do not follow ACE syntax and are consequently not valid. Interpretation rules resolve the anaphoric references in (3): the tie and it of the second sentence refer to a new tie of the first sentence, while his and the man of the second sentence refer to a man of the first sentence. Thus an ACE text is a coherent entity of anaphorically linked sentences. The Attempto Parsing Engine (APE) translates ACE texts unambiguously into discourse representation structures (DRS) that use a variant of the language of first-order logic. A DRS can be further translated into other formal languages, for instance AceRules with various semantics, OWL, and SWRL. Translating an ACE text into (a fragment of) first-order logic allows users to reason about the text, for instance to verify, to validate, and to query it. == Overview == As an overview of the current version 6.6 of ACE this section: Briefly describes the vocabulary Gives an account of the syntax Summarises the handling of ambiguity Explains the processing of anaphoric references. === Vocabulary === The vocabulary of ACE comprises: Predefined function words (e.g. determiners, conjunctions) Predefined phrases (e.g. "it is false that ...", "it is possible that ...") Content words (e.g. nouns, verbs, adjectives, adverbs). === Grammar === The grammar of ACE defines and constrains the form and the meaning of ACE sentences and texts. ACE's grammar is expressed as a set of construction rules. The meaning of sentences is described as a small set of interpretation rules. A Troubleshooting Guide describes how to use ACE and how to avoid pitfalls. ==== ACE texts ==== An ACE text is a sequence of declarative sentences that can be anaphorically interrelated. Furthermore, ACE supports questions and commands. ==== Simple sentences ==== A simple sentence asserts that something is the case—a fact, an event, a state. The temperature is −2 °C. A customer inserts 2 cards. A card and a code are valid. Simple ACE sentences have the following general structure: subject + verb + complements + adjuncts Every sentence has a subject and a verb. Complements (direct and indirect objects) are necessary for transitive verbs (insert something) and ditransitive verbs (give something to somebody), whereas adjuncts (adverbs, prepositional phrases) are optional. All elements of a simple sentence can be elaborated upon to describe the situation in more detail. To further specify the nouns customer and card, we could add adjectives: A trusted customer inserts two valid cards. possessive nouns and of-prepositional phrases: John's customer inserts a card of Mary. or variables as appositions: John inserts a card A. Other modifications of nouns are possible through relative sentences: A customer who is trusted inserts a card that he owns. which are described below since they make a sentence composite. We can also detail the insertion event, e.g. by adding an adverb: A customer inserts some cards manually. or, equivalently: A customer manually inserts some cards. or, by adding prepositional phrases: A customer inserts some cards into a slot. We can combine all of these elaborations to arrive at: John's customer who is trusted inserts a valid card of Mary manually into a slot A. ==== Composite sentences ==== Composite sentences are recursively built from simpler sentences through coordination, subordination, quantification, and negation. Note that ACE composite sentences overlap with what linguists call compound sentences and complex sentences. ===== Coordination ===== Coordination by and is possible between sentences and between phrases of the same syntactic type. A customer inserts a card and the machine checks the code. There is a customer who inserts a card and who enters a code. A customer inserts a card and enters a code. An old and trusted customer enters a card and a code. Note that the coordination of the noun phrases a card and a code represents a plural object. Coordination by or is possible between sentences, verb phrases, and relative clauses. A customer inserts a card or the machine checks the code. A customer inserts a card or enters a code. A customer owns a card that is invalid or that is damaged. Coordination by and and or is governed by the standard binding order of logic, i.e. and binds stronger than or. Commas can be used to override the standard binding order. Thus the sentence: A customer inserts a VisaCard or inserts a MasterCard, and inserts a code. means that the customer inserts a VisaCard and a code, or alternatively a MasterCard and a code. ===== Subordination ===== There are four constructs of subordination: relative sentences, if-then sentences, modality, and sentence subordination. Relative sentences starting with who, which, and that allow to add detail to nouns: A customer who is trusted inserts a card that he owns. With the help of if-then sentences we can specify conditional or hypothetical situations: If a card is valid then a customer inserts it. Note the anaphoric reference via the pronoun it in the then-part to the noun phrase a card in the if-part. Modality allows us to express possibility and necessity: A trusted customer can/must insert a card. It is possible/necessary that a trusted customer inserts a card. Sentence subordination comes in various forms: It is true/false that a customer inserts a card. It is not provable that a customer inserts a card. A clerk believes that a customer inserts a card. ===== Quantification ===== Quantification allows us to speak about all objects of a certain class (universal quantification), or to denote explicitly the existence of at least one object of this class (existential quantification). The textual occurrence of a universal or existential quantifier opens its scope that extends to the end of the sentence, or in coordinations to the end of the respective coordinated sentence. To express that all involved customers insert cards we can write Every customer inserts a card. This sentence means that each customer inserts a card that may, or may not, be the same as the one inserted by another customer. To specify that all customers insert the same card—however unrealistic that situation seems—we can write: A card is inserted by every customer. or, equivalently: There is a card that every customer inserts. To state that every card is inserted by a customer we write: Every card is inserted by a customer. or, somewhat indirectly: For every card there is a customer who inserts it. ===== Negation ===== Negation allows us to express that something is not the case: A customer does not insert a card. A card is not valid. To negate something for all objects of a certain class one uses no: No customer inserts more than 2 cards. or, there is no: There is no customer who inserts a card. To negate a complete statement one uses sentence negation: It is false that a customer inserts a card. These forms of negation are logical negations, i.e. they state that something is provably not the case. Negation as failure states that a state of affairs cannot be proved, i.e. there is no information whether the state of affairs is the case or not. It is not provable that a customer inserts a card. ==== Queries ==== ACE supports two forms of queries: yes/no-queries and wh-queries. Yes/no-queries ask for the existence or non-existence of a specified situation. If we specified: A customer inserts a card. then we can ask: Does a customer insert a card? to get a positive answer. Note that interrogative sentences always end with a question mark. With the help of wh-queries, i.e. queries with query words, we can interrogate a text for details of the specified situation. If we specified: A

  Read more →