MuZero is a computer program developed by artificial intelligence research company DeepMind, a subsidiary of Google, to master games without knowing their rules and underlying dynamics. Its release in 2019 included benchmarks of its performance in Go, chess, shogi, and a suite of 57 different Atari games. The algorithm uses an approach similar to AlphaZero, where a combination of a tree-based search and a learned model is deployed. It matched AlphaZero's performance in chess and shogi, improved on its performance in Go, and improved on the state of the art in mastering a suite of 57 Atari games (the Arcade Learning Environment), a visually-complex domain. MuZero was trained via self-play, with no access to rules, opening books, or endgame tablebases. The trained algorithm used the same convolutional and residual architecture as AlphaZero, but with 20 percent fewer computation steps per node in the search tree. == History == MuZero really is discovering for itself how to build a model and understand it just from first principles. On November 19, 2019, the DeepMind team released a preprint introducing MuZero. === Derivation from AlphaZero === MuZero (MZ) is a combination of the high-performance planning of the AlphaZero (AZ) algorithm with approaches to model-free reinforcement learning. The combination allows for more efficient training in classical planning regimes, such as Go, while also handling domains with much more complex inputs at each stage, such as visual video games. MuZero was derived directly from AZ code, sharing its rules for setting hyperparameters. Differences between the approaches include: AZ's planning process uses a simulator. The simulator knows the rules of the game. It has to be explicitly programmed. A neural network then predicts the policy and value of a future position. Perfect knowledge of game rules is used in modeling state transitions in the search tree, actions available at each node, and termination of a branch of the tree. MZ does not have access to the rules, and instead learns one with neural networks. AZ has a single model for the game (from board state to predictions); MZ has separate models for representation of the current state (from board state into its internal embedding), dynamics of states (how actions change representations of board states), and prediction of policy and value of a future position (given a state's representation). MZ's hidden model may be complex, and it may turn out it can host computation; exploring the details of the hidden model in a trained instance of MZ is a topic for future exploration. MZ does not expect a two-player game where winners take all. It works with standard reinforcement-learning scenarios, including single-agent environments with continuous intermediate rewards, possibly of arbitrary magnitude and with time discounting. AZ was designed for two-player games that could be won, drawn, or lost. === Comparison with R2D2 === The previous state of the art technique for learning to play the suite of Atari games was R2D2, the Recurrent Replay Distributed DQN. MuZero surpassed both R2D2's mean and median performance across the suite of games, though it did not do better in every game. == Training and results == MuZero used 16 third-generation tensor processing units (TPUs) for training, and 1000 TPUs for selfplay for board games, with 800 simulations per step and 8 TPUs for training and 32 TPUs for selfplay for Atari games, with 50 simulations per step. AlphaZero used 64 second-generation TPUs for training, and 5000 first-generation TPUs for selfplay. As TPU design has improved (third-generation chips are 2x as powerful individually as second-generation chips, with further advances in bandwidth and networking across chips in a pod), these are comparable training setups. R2D2 was trained for 5 days through 2M training steps. === Initial results === MuZero matched AlphaZero's performance in chess and shogi after roughly 1 million training steps. It matched AZ's performance in Go after 500,000 training steps and surpassed it by 1 million steps. It matched R2D2's mean and median performance across the Atari game suite after 500 thousand training steps and surpassed it by 1 million steps, though it never performed well on 6 games in the suite. == Reactions and related work == MuZero was viewed as a significant advancement over AlphaZero, and a generalizable step forward in unsupervised learning techniques. The work was seen as advancing understanding of how to compose systems from smaller components, a systems-level development more than a pure machine-learning development. While only pseudocode was released by the development team, Werner Duvaud produced an open source implementation based on that. MuZero has been used as a reference implementation in other work, for instance as a way to generate model-based behavior. In late 2021, a more efficient variant of MuZero was proposed, named EfficientZero. It "achieves 194.3 percent mean human performance and 109.0 percent median performance on the Atari 100k benchmark with only two hours of real-time game experience". In early 2022, a variant of MuZero was proposed to play stochastic games (for example 2048, backgammon), called Stochastic MuZero, which uses afterstate dynamics and chance codes to account for the stochastic nature of the environment when training the dynamics network.
Device-independent pixel
A device-independent pixel (also: density-independent pixel, dip, dp) is a unit of length. A typical use is to allow mobile device software to scale the display of information and user interaction to different screen sizes. The abstraction allows an application to work in pixels as a measurement, while the underlying graphics system converts the abstract pixel measurements of the application into real pixel measurements appropriate to the particular device. For example, on the Android operating system a device-independent pixel is equivalent to one physical pixel on a 160 dpi screen, while the Windows Presentation Foundation specifies one device-independent pixel as equivalent to 1/96th of an inch. As dp is a physical unit it has an absolute value which can be measured in traditional units, e.g. for Android devices 1 dp equals 1/160 of inch or 0.15875 mm. While traditional pixels only refer to the display of information, device-independent pixels may also be used to measure user input such as input on a touch screen device.
Smoothing
In statistics and image processing, to smooth a data set is to create an approximating function that attempts to capture important patterns in the data, while leaving out noise or other fine-scale structures/rapid phenomena. In smoothing, the data points of a signal are modified so individual points higher than the adjacent points (presumably because of noise) are reduced, and points that are lower than the adjacent points are increased, leading to a smoother signal. Reducing noise by smoothing may aid in data analysis in two notable ways: Help uncover more meaningful information from the underlying data, such as trends. Provide analyses that are both flexible and robust. Many different algorithms are used in smoothing, most commonly binning, kernels, and local weighted regression. == Compared to curve fitting == Smoothing may be distinguished from the related and partially overlapping concept of curve fitting in the following ways: curve fitting often involves the use of an explicit function form for the result, whereas the immediate results from smoothing are the "smoothed" values with no later use made of a functional form if there is one; the aim of smoothing is to give a general idea of relatively slow changes of value with little attention paid to the close matching of data values, while curve fitting concentrates on achieving as close a match as possible. smoothing methods often have an associated tuning parameter which is used to control the extent of smoothing. Curve fitting will adjust any number of parameters of the function to obtain the 'best' fit. == Linear smoothers == In the case that the smoothed values can be written as a linear transformation of the observed values, the smoothing operation is known as a linear smoother; the matrix representing the transformation is known as a smoother matrix or hat matrix. The operation of applying such a matrix transformation is called convolution. Thus the matrix is also called convolution matrix or a convolution kernel. In the case of simple series of data points (rather than a multi-dimensional image), the convolution kernel is a one-dimensional vector. == Algorithms == One of the most common algorithms is the "moving average", often used to try to capture important trends in repeated statistical surveys. In image processing and computer vision, smoothing ideas are used in scale space representations. The simplest smoothing algorithm is the "rectangular" or "unweighted sliding-average smooth". This method replaces each point in the signal with the average of "m" adjacent points, where "m" is a positive integer called the "smooth width". Usually m is an odd number. The triangular smooth is like the rectangular smooth except that it implements a weighted smoothing function. Some specific smoothing and filter types, with their respective uses, pros and cons are:
Acoustic model
An acoustic model is used in automatic speech recognition to represent the relationship between an audio signal and the phonemes or other linguistic units that make up speech. The model is learned from a set of audio recordings and their corresponding transcripts. It is created by taking audio recordings of speech, and their text transcriptions, and using software to create statistical representations of the sounds that make up each word. == Background == Modern speech recognition systems use both an acoustic model and a language model to represent the statistical properties of speech. The acoustic model models the relationship between the audio signal and the phonetic units in the language. The language model is responsible for modeling the word sequences in the language. These two models are combined to get the top-ranked word sequences corresponding to a given audio segment. Most modern speech recognition systems operate on the audio in small chunks known as frames with an approximate duration of 10ms per frame. The raw audio signal from each frame can be transformed by applying the mel-frequency cepstrum. The coefficients from this transformation are commonly known as mel-frequency cepstral coefficients (MFCCs) and are used as an input to the acoustic model along with other features. Recently, the use of convolutional neural networks has led to major improvements in acoustic modeling. == Speech audio characteristics == Audio can be encoded at different sampling rates (i.e. samples per second – the most common being: 8, 16, 32, 44.1, 48, and 96 kHz), and different bits per sample (the most common being: 8-bits, 16-bits, 24-bits or 32-bits). Speech recognition engines work best if the acoustic model they use was trained with speech audio which was recorded at the same sampling rate/bits per sample as the speech being recognized. == Telephony-based speech recognition == The limiting factor for telephony based speech recognition is the bandwidth at which speech can be transmitted. For example, a standard land-line telephone only has a bandwidth of 64 kbit/s at a sampling rate of 8 kHz and 8-bits per sample (8000 samples per second 8-bits per sample = 64000 bit/s). Therefore, for telephony based speech recognition, acoustic models should be trained with 8 kHz/8-bit speech audio files. In the case of voice over IP, the codec determines the sampling rate/bits per sample of speech transmission. Codecs with a higher sampling rate/bits per sample for speech transmission (which improve the sound quality) necessitate acoustic models trained with audio data that matches that sampling rate/bits per sample. == Desktop-based speech recognition == For speech recognition on a standard desktop PC, the limiting factor is the sound card. Most sound cards today can record at sampling rates of between 16–48 kHz of audio, with bit rates of 8- to 16-bits per sample, and playback at up to 96 kHz. As a general rule, a speech recognition engine works better with acoustic models trained with speech audio data recorded at higher sampling rates/bits per sample. But using audio with too high a sampling rate/bits per sample can slow the recognition engine down. A compromise is needed. Thus for desktop speech recognition, the current standard is acoustic models trained with speech audio data recorded at sampling rates of 16 kHz/16 bits per sample.
Automaton
An automaton ( ; pl.: automata or automatons) is a relatively self-operating machine or control mechanism designed to automatically follow a sequence of operations or respond to predetermined instructions. Some automata, such as bellstrikers in mechanical clocks, are designed to give the illusion to the casual observer that they are operating under their own power or will, like a mechanical robot. The term has long been commonly associated with automated puppets that resemble moving humans or animals, built to impress and/or to entertain people. Animatronics are a modern type of automata with electronics, often used for the portrayal of characters or creatures in films and in theme park attractions. == Etymology == The word automaton is the latinization of the Ancient Greek automaton (αὐτόματον), which means "acting of one's own will". It was first used by Homer to describe an automatic door opening, or automatic movement of wheeled tripods. It is more often used to describe non-electronic moving machines, especially those that have been made to resemble human or animal actions, such as the jacks on old public striking clocks, or the cuckoo and any other animated figures on a cuckoo clock. == History == === Ancient === There are many examples of automata in Greek mythology: Hephaestus created automata for his workshop; Talos was an artificial man of bronze; King Alkinous of the Phaiakians employed gold and silver watchdogs. According to Aristotle, Daedalus used quicksilver to make his wooden statue of Aphrodite move. In other Greek legends he used quicksilver to install voice in his moving statues. The automata in the Hellenistic world were intended as tools, toys, religious spectacles, or prototypes for demonstrating basic scientific principles. Numerous water-powered automata were built by Ktesibios, a Greek inventor and the first head of the Great Library of Alexandria; for example, he "used water to sound a whistle and make a model owl move. He had invented the world's first 'cuckoo clock'". This tradition continued in Alexandria with inventors such as the Greek mathematician Hero of Alexandria (sometimes known as Heron), whose writings on hydraulics, pneumatics, and mechanics described siphons, a fire engine, a water organ, the aeolipile, and a programmable cart. Philo of Byzantium was famous for his inventions. Complex mechanical devices are known to have existed in Hellenistic Greece, though the only surviving example is the Antikythera mechanism, the earliest known analog computer. The clockwork is thought to have come originally from Rhodes, where there was apparently a tradition of mechanical engineering; the island was renowned for its automata; to quote Pindar's seventh Olympic Ode: The animated figures stand Adorning every public street And seem to breathe in stone, or move their marble feet. However, the information gleaned from recent scans of the fragments indicate that it may have come from the colonies of Corinth in Sicily and implies a connection with Archimedes. According to Jewish legend, King Solomon used his wisdom to design a throne with mechanical animals which hailed him as king when he ascended it; upon sitting down an eagle would place a crown upon his head, and a dove would bring him a Torah scroll. It is also said that when King Solomon stepped upon the throne, a mechanism was set in motion. As soon as he stepped upon the first step, a golden ox and a golden lion each stretched out one foot to support him and help him rise to the next step. On each side, the animals helped the King up until he was comfortably seated upon the throne. In ancient China, a curious account of automata is found in the Lie Zi text, believed to have originated around 400 BCE and compiled around the fourth century CE. Within it there is a description of a much earlier encounter between King Mu of Zhou (1023–957 BCE) and a mechanical engineer known as Yan Shi, an 'artificer'. The latter proudly presented the king with a very realistic and detailed life-size, human-shaped figure of his mechanical handiwork: The king stared at the figure in astonishment. It walked with rapid strides, moving its head up and down, so that anyone would have taken it for a live human being. The artificer touched its chin, and it began singing, perfectly in tune. He touched its hand, and it began posturing, keeping perfect time...As the performance was drawing to an end, the robot winked its eye and made advances to the ladies in attendance, whereupon the king became incensed and would have had Yen Shih [Yan Shi] executed on the spot had not the latter, in mortal fear, instantly taken the robot to pieces to let him see what it really was. And, indeed, it turned out to be only a construction of leather, wood, glue and lacquer, variously coloured white, black, red and blue. Examining it closely, the king found all the internal organs complete—liver, gall, heart, lungs, spleen, kidneys, stomach and intestines; and over these again, muscles, bones and limbs with their joints, skin, teeth and hair, all of them artificial...The king tried the effect of taking away the heart, and found that the mouth could no longer speak; he took away the liver and the eyes could no longer see; he took away the kidneys and the legs lost their power of locomotion. The king was delighted. Other notable examples of automata include Archytas' dove, mentioned by Aulus Gellius. Similar Chinese accounts of flying automata are written of the 5th century BC Mohist philosopher Mozi and his contemporary Lu Ban, who made artificial wooden birds (ma yuan) that could successfully fly according to the Han Fei Zi and other texts. === Medieval === The manufacturing tradition of automata continued in the Greek world well into the Middle Ages. On his visit to Constantinople in 949 ambassador Liutprand of Cremona described automata in the emperor Theophilos' palace, including "lions, made either of bronze or wood covered with gold, which struck the ground with their tails and roared with open mouth and quivering tongue," "a tree of gilded bronze, its branches filled with birds, likewise made of bronze gilded over, and these emitted cries appropriate to their species" and "the emperor's throne" itself, which "was made in such a cunning manner that at one moment it was down on the ground, while at another it rose higher and was to be seen up in the air." Similar automata in the throne room (singing birds, roaring and moving lions) were described by Luitprand's contemporary the Byzantine emperor Constantine Porphyrogenitus, in his book De Ceremoniis (Perì tês Basileíou Tákseōs). In the mid-8th century, the first wind powered automata were built: "statues that turned with the wind over the domes of the four gates and the palace complex of the Round City of Baghdad". The "public spectacle of wind-powered statues had its private counterpart in the 'Abbasid palaces where automata of various types were predominantly displayed." Also in the 8th century, the Muslim alchemist, Jābir ibn Hayyān (Geber), included recipes for constructing artificial snakes, scorpions, and humans that would be subject to their creator's control in his coded Book of Stones. In 827, Abbasid caliph al-Ma'mun had a silver and golden tree in his palace in Baghdad, which had the features of an automatic machine. There were metal birds that sang automatically on the swinging branches of this tree built by Muslim inventors and engineers. The Abbasid caliph al-Muqtadir also had a silver and golden tree in his palace in Baghdad in 917, with birds on it flapping their wings and singing. In the 9th century, the Banū Mūsā brothers invented a programmable automatic flute player and which they described in their Book of Ingenious Devices. Al-Jazari described complex programmable humanoid automata amongst other machines he designed and constructed in the Book of Knowledge of Ingenious Mechanical Devices in 1206. His automaton was a boat with four automatic musicians that floated on a lake to entertain guests at royal drinking parties. His mechanism had a programmable drum machine with pegs (cams) that bump into little levers that operate the percussion. The drummer could be made to play different rhythms and drum patterns if the pegs were moved around. Al-Jazari constructed a hand washing automaton first employing the flush mechanism now used in modern toilets. It features a female automaton standing by a basin filled with water. When the user pulls the lever, the water drains and the automaton refills the basin. His "peacock fountain" was another more sophisticated hand washing device featuring humanoid automata as servants who offer soap and towels. Mark E. Rosheim describes it as follows: "Pulling a plug on the peacock's tail releases water out of the beak; as the dirty water from the basin fills the hollow base a float rises and actuates a linkage which makes a servant figure appear from behind a door under the peacock and offer soap.
Spotify Kids
Spotify Kids is a Swedish kid-friendly Music streaming service developed by Spotify. It offers curated content for children, including music, audiobooks, lullabies, and bedtime stories, while providing their parents with parental controls. The service is only available to subscribers to Spotify's Premium Family subscription plan. == Function == Spotify Kids is a Swedish Kid-friendly Music Streaming Service that allows children to browse Spotify with parental controls. Using the app, parents can view their children's listening history, block specific songs, and share playlists with their children. The app also includes sing-along songs, playlists designed for young children, and curated audiobooks, lullabies, and bedtime stories. Access is included in Spotify's Premium Family subscription plan, and is exclusive to subscribers to the plan. Users can configure the app for a specific age group upon first launch. The playlists on Spotify Kids are curated by groups including Discovery Kids, Nickelodeon, Universal Pictures, and The Walt Disney Company. All content on the Spotify Kids app is curated by editors. As of March 2021, there were roughly 8,000 songs available on the platform. The design of the Spotify Kids app is colorful, and user interface varies depending on the age group for which the app is configured. Spotify Kids is designed to comply with consent and data collection regulations for apps used by children. TechCrunch explains that it is "designed on a grand scale to drive subscriptions to Spotify's top-tier $14.99-per-month Premium Family Plan." == Release == After being beta tested in Ireland in October 2019, it was released as a beta across the United Kingdom on February 11, 2020. It was later released in Sweden, Denmark, Australia, New Zealand, Mexico, Argentina, and Brazil. On March 31, 2021, it was made available in France, Canada, and the United States.
Drops (app)
Drops is a language learning app that was created in Estonia by Daniel Farkas and Mark Szulyovszky in 2015. It is the second product from the company, after their first app, LearnInvisible, had issues in retaining a user's engagement over the required time period. The languages available include Native Hawaiian and Māori, and was classified as one of the fifty "Most Innovative Companies" for 2019 by Fast Company. The company partnered with Global Eagle Entertainment to include Travel Talk, a feature intended to focus on words and phrases frequently used by travelers. At the beginning of the COVID-19 pandemic in March 2020, the number of users increased by 55 percent in the United States and 92 percent in the United Kingdom. Droplets, a language app for children, includes profiles for multiple teachers working with remote students. The company also produces an app called Scripts, intended to help users learn to write alphabets. The app was purchased by the Norwegian company Kahoot! on 24 November 2020.