Yasuo Matsuyama (born March 23, 1947) is a Japanese researcher in machine learning and human-aware information processing. Matsuyama is a Professor Emeritus and an Honorary Researcher of the Research Institute of Science and Engineering of Waseda University. == Early life and education == Matsuyama received his bachelor’s, master’s and doctoral degrees in electrical engineering from Waseda University in 1969, 1971, and 1974 respectively. The dissertation title for the Doctor of Engineering is Studies on Stochastic Modeling of Neurons. There, he contributed to the spiking neurons with stochastic pulse-frequency modulation. Advisors were Jun’ichi Takagi, Kageo, Akizuki, and Katsuhiko Shirai. Upon the completion of the doctoral work at Waseda University, he was dispatched to the United States as a Japan-U.S. exchange fellow by the joint program of the Japan Society for the Promotion of Science, Fulbright Program, and the Institute of International Education. Through this exchange program, he completed his Ph.D. program at Stanford University in 1978. The dissertation title is Process Distortion Measures and Signal Processing. There, he contributed to the theory of probabilistic distortion measures and its applications to speech encoding with spectral clustering or vector quantization. His advisor was Robert. M. Gray. == Career == From 1977 to 1078, Matsuyama was a research assistant at the Information Systems Laboratory of Stanford University Archived 2018-03-16 at the Wayback Machine. From 1979 to 1996, he was a faculty of Ibaraki University, Japan (the final position was a professor and chairperson of the Information and System Sciences Major). Since 1996, he was a Professor of Waseda University, Department of Computer Science and Engineering. From 2011 to 2013, he was the director of the Media Network Center of Waseda University. At the 2011 Tōhoku earthquake and tsunami of March 11, 2011, he was in charge of the safety inquiry of 65,000 students, staffs and faculties. Since 2017, Matsuyama is a Professor Emeritus and an Honorary Researcher of the Research Institute of Science and Engineering of Waseda University. Since 2018, he serves as an acting president of the Waseda Electrical Engineering Society. == Work == Matsuyama’s works on machine learning and human-aware information processing have dual foundations. Studies on the competitive learning (vector quantization) for his Ph.D. at Stanford University brought about his succeeding works on machine learning contributions. Studies on stochastic spiking neurons for his Dr. Engineering at Waseda University set off applications of biological signals to the machine learning. Thus, his works can be grouped reflecting these dual foundations. Statistical machine learning algorithms: The use of the alpha-logarithmic likelihood ratio in learning cycles generated the alpha-EM algorithm (alpha-Expectation maximization algorithm). Because the alpha-logarithm includes the usual logarithm, the alpha-EM algorithm contains the EM-algorithm (more precisely, the log-EM algorithm). The merit of the speedup by the alpha-EM over the log-EM is due to the ability to utilize the past information. Such a usage of the messages from the past brought about the alpha-HMM estimation algorithm (alpha-hidden Markov model estimation algorithm) that is a generalized and faster version of the hidden Markov model estimation algorithm (HMM estimation algorithm). Competitive learning on empirical data: Starting from the speech compression studies at Stanford, Matsuyama developed generalized competitive learning algorithms; the harmonic competition and the multiple descent cost competition. The former realizes the multiple-object optimization. The latter admits deformable centroids. Both algorithms generalize the batch-mode vector quantization (simply called, vector quantization) and the successive-mode vector quantization (or, called learning vector quantization). A hierarchy from the alpha-EM to the vector quantization: Matsuyama contributed to generate and identify the hierarchy of the above algorithms. Alpha-EM ⊃ log-EM ⊃ basic competitive learning (vector quantization, VQ; or clustering). On the class of the vector quantization and competitive learning, he contributed to generate and identify the hierarchy of VQs. VQ ⇔ {batch mode VQ, and learning VQ} ⊂ {harmonic competition} ⊂ {multiple descent cost competition}. Applications to Human-aware information processing: The dual foundations of his led to the applications to huma-aware information processing. Retrieval systems for similar images and videos. Bipedal humanoid operations via invasive and noninvasive brain signals as well as gestures. Continuous authentication of uses by brain signals. Self-organization and emotional feature injection based on the competitive learning. Decomposition of DNA sequences by the independent component analysis (US Patent: US 8,244,474 B2). Data compression of speech signals by the competitive learning. The above theories and applications work as contributions to IoCT (Internet of Collaborative Things) and IoXT (http://www.asc-events.org/ASC17/Workshop.php Archived 2018-02-06 at the Wayback Machine). == Awards and honors == 2016: e-Teaching Award of Waseda University 2015: Best Textbook Award by the Japanese Society of Information Processing 2014: Fellow of the Japanese Society of Information Processing 2013: IEEE Life Fellow 2008: Y. Dote Memorial Best Paper Award of CSTST 2008 from ACM and IEEE 2006: LSI Intellectual Property Design Award from the LSI IP Committee 2004: Best Paper Award for Application Oriented Research from Asia Pacific Neural Network Assembly 2002: Fellow Award from the Institute of Electronics, Information and Communication Engineers. 2001: Telecommunication System Major Award of the Telecommunications Advancement Foundation 2001: Outstanding Paper Award of IEEE Transactions on Neural Networks Archived 2013-01-17 at the Wayback Machine 1998: Fellow Award from IEEE for contributions to learning algorithms with competition. 1992: Best Paper Award from the Institute of Electronics, Information and Communication Engineers 1989: Telecommunication System Promotion Award of the Telecommunications Advancement Foundation
Doubao
Doubao (Chinese: 豆包) is an artificial intelligence assistant developed by ByteDance. == History == The chatbot was launched in August 2023. By November 2024, it had become China's most popular AI chatbot, with approximately 60 million monthly active users according to industry analytics. == Design == Doubao is powered by Volcano Engine (Volcengine), 120 trillion tokens consumed per day. == Variants == === Dola === The international version of Doubao is Dola which was launched in August 2023 as Cici. Dola is powered by OpenAI's GPT series of large language models and by Google's Gemini.
Concordance (publishing)
A concordance is an alphabetical list of the principal words used in a book or body of work, listing every instance of each word with its immediate context. Historically, concordances have been compiled only for works of special importance, such as the Vedas, Bible, Qur'an or the works of Shakespeare, James Joyce or classical Latin and Greek authors, because of the time, difficulty, and expense involved in creating a concordance in the pre-computer era. A concordance is more than an index, with additional material such as commentary, definitions and topical cross-indexing which makes producing one a labor-intensive process even when assisted by computers. In the precomputing era, search technology was unavailable, and a concordance offered readers of long works such as the Bible something comparable to search results for every word that they would have been likely to search for. Today, the ability to combine the result of queries concerning multiple terms (such as searching for words near other words) has reduced interest in concordance publishing. In addition, mathematical techniques such as latent semantic indexing have been proposed as a means of automatically identifying linguistic information based on word context. A bilingual concordance is a concordance based on aligned parallel text. A topical concordance is a list of subjects that a book covers (usually The Bible), with the immediate context of the coverage of those subjects. Unlike a traditional concordance, the indexed word does not have to appear in the verse. The best-known topical concordance is Nave's Topical Bible. The first Bible concordance was compiled for the Vulgate Bible by Hugh of St Cher (d.1262), who employed 500 friars to assist him. In 1448, Rabbi Mordecai Nathan completed a concordance to the Hebrew Bible. It took him ten years. A concordance to the Greek New Testament was published in 1546 by Sixt Birck, and the Septuagint was done a by Conrad Kircher in 1602. The first concordance to the English Bible was published in 1550 by John Merbecke. According to Cruden, it did not employ the verse numbers devised by Robert Stephens in 1545, but "the pretty large concordance" of Mr Cotton did. Then followed Cruden's Concordance and Strong's Concordance. == Use in linguistics == Concordances are frequently used in linguistics, when studying a text. For example: comparing different usages of the same word analysing keywords analysing word frequencies finding and analysing phrases and idioms finding translations of subsentential elements, e.g. terminology, in bitexts and translation memories creating indexes and word lists (also useful for publishing) Concordancing techniques are widely used in national text corpora such as American National Corpus (ANC), British National Corpus (BNC), and Corpus of Contemporary American English (COCA) available on-line. Stand-alone applications that employ concordancing techniques are known as concordancers or more advanced corpus managers. Some of them have integrated part-of-speech taggers (POS taggers) and enable the user to create their own POS-annotated corpora to conduct various types of searches adopted in corpus linguistics. == Inversion == The reconstruction of the text of some of the Dead Sea Scrolls involved a concordance. Access to some of the scrolls was governed by a "secrecy rule" that allowed only the original International Team or their designates to view the original materials. After the death of Roland de Vaux in 1971, his successors repeatedly refused to even allow the publication of photographs to other scholars. This restriction was circumvented by Martin Abegg in 1991, who used a computer to "invert" a concordance of the missing documents made in the 1950s which had come into the hands of scholars outside of the International Team, to obtain an approximate reconstruction of the original text of 17 of the documents. This was soon followed by the release of the original text of the scrolls.
AI: When a Robot Writes a Play
AI: When a Robot Writes a Play (in Czech: AI: Když robot píše hru) is a 2021 experimental theatre play, where 90% of its script was automatically generated by artificial intelligence (the GPT-2 language model). The play is in Czech language, but an English version of the script also exists. == Creation == The play is the first result of the THEaiTRE research project, aiming to commemorate the centenary of the R.U.R. play by Karel Čapek by investigating to what extent artificial intelligence could be used to create theatre play scripts. The script of the play was created using the THEaiTRobot tool, based on the GPT-2 language model. First, the play dramaturge, David Košťák, described the initial setting of each scene in a few sentences, and wrote the first line for each character. Next, THEaiTRobot suggested a continuation of the script, which the dramaturge could use, reject, or use part of it and let the tool generate a new continuation. Another option was to manually insert another line or a scenic remark. The script was generated in English and was automatically translated to Czech by the state-of-the-art CUBBITT machine translation tool. The resulting script was then further post-edited by the dramaturge. The resulting script was made freely available for non-commercial use both in English and in Czech, with marked manually inserted texts and manual edits. The analysis shows that 90% of the English script is automatically generated, with 10% manually written or manually post-edited. In the Czech script, a larger amount of edits were made, but the analysis claims that these additional edits are corrections of errors of the automated translation and stylistic corrections which do not change the meaning of the lines as represented by the English script, but rather bring the Czech script closer to the English one. == Characters == The play contains 9 characters. The Robot appears in all the scenes, while each of the other characters appears in only one scene. Robot – The lead character, a male humanoid robot. Master – An old man, the creator of the Robot. Boy – A schoolboy. Masseuse – A sex worker in a brothel. Stranger – An engineer. Man. Psychologist. Administrator – A female clerk at an employment agency. Actress – A film actress and a model in a robot-like costume. == Plot == The play is composed of 8 scenes. It tells the story of a humanoid robot, who encounters 8 other characters and engages into various typically human situations and activities, related to death, love, sex, violence, etc. The individual scenes are not tightly linked, but there are some linking points, such as the central character of the robot or some repeated and developing themes, such as the robot's search for love. The scenes often contain some absurd turns and it is often hard to find sense in them. It is therefore a very complicated piece interpretationally, requiring the director and the actors to invest a lot of effort and creativity in finding a meaningful interpretation which would not deviate from the script. In the interpretation by Švanda theatre, who premiered the play and who also participated on the creation of the script, the scenes typically contain non-verbally expressed content which can add a lot to the meaning of the scene compared to what is contained in the actual script (as the script only contains the lines said by the characters). === Scene 1: Death === The play opens by the Robot parting with his dying Master. The Master gives the Robot several last lessons and talks with him about death, soul, and love. === Scene 2: Sense of Humour === In the second scene, the Robot meets a sad and angry Boy, who complains that he wants to go to school, that his girlfriend is crazy, that he wants to buy a car, etc. The Robot tries to help the Boy by giving him advice, but the Boy's reactions are quite negative and irritated. The Boy then repeatedly asks the Robot to tell him a joke; the Robot keeps refusing, but ultimately tells the following joke: When you are dead. When your children are dead. When your grandchildren are dead, I will be still alive. === Scene 3: Nightclub === The Robot wants to feel pleasure, so he goes to a "night club" (a brothel), where he meets a "Masseuse" (a prostitute). The Robot is initially "a bit cold", but eventually manages to enjoy the experience and falls in love with the Masseuse. In the Švanda theatre performance, the Robot and the Masseuse seem to have a sort of virtual sex without touching each other, reminiscent of the sex scene in Demolition Man. === Scene 4: Fear of the Dark === It is the night. The Robot is standing under a lamp, unable to move away from the light as he finds that he is afraid of the dark. He meets a Stranger, an engineer who tells him that robots don't have feelings and that people cannot be trusted, and keeps hurting him. In the Švanda theatre performance, the Man repeatedly zaps the Robot with some kind of electric pulse. === Scene 5: Killer Robot === A Man approaches the Robot and repeatedly asks him to kill him. Instead, the Robot sticks a finger into the Man's anus, which leads to an argument between the Man and the Robot. === Scene 6: Burn Out === The Robot meets a Psychologist, who keeps asking him lots of questions regarding his life, burnout feeling, love, relationships, and emotions. They also talk about the Robot using a device called emotion machine which helps him to get rid of stress. === Scene 7: Search for Job === The Robot comes to an employment agency. He meets an Administrator and asks her to help him find a job. He expresses the wish to become an actor, and talks about his experience as a clown. He reveals his name to be Troy McClure, which is a character from The Simpsons who is an actor. In the Švanda theatre performance, the Administrator starts to seduce the Robot once his name is revealed, which he keeps ignoring; the Administrator then becomes irritated. === Scene 8: Love at First Sight === The Robot meets a human Actress in a robotic costume and falls in love with her immediately. The Actress is first reluctant, but the Robot manages to seduce her and she also falls in love with him. The Robot tells her about a binary world, in which he lives and where he will also take her. Ultimately, the Actress agrees, and the whole play concludes by the Robot and the Actress promising each to other to always be together. In the Švanda theatre performance, the Robot does not have a physical body in this scene, we can only hear his voice and see a pulsating light (based on the line in the script where the Robot says: "I have no body. So I don't need to wear clothes. You can't see me, you only hear me."), and the Actress eventually also agrees to lose her physical body so that she can be with the Robot forever. == Theatrical performances == The play premiered on 26 February 2021 in Švanda Theatre in Prague, Czech Republic, directed by Daniel Hrbek. Due to the COVID-19 pandemic, the play was not played in front of a live audience, but it was broadcast online, in Czech language with English subtitles. The play was followed by a panel discussion by the project members and experts on artificial intelligence. The premiere was viewed by 13,498 spectators worldwide. A short trailer of the premiere is available on YouTube. In 2021, after the opening of the theatres in the Czech Republic to spectators, the play can be viewed at Švanda Theatre. The performance takes approximately 60 minutes, and is followed by a discussion of the creators with the audience. The derniere is planned for 4 February 2023. == Reception == The play received a number of reviews, both in its country of origin as well as internationally. It is praised as first of its kind, although some reviewers note the similarity to previous works, such as the musical Beyond the Fence, the play Lifestyle of the Richard and Family, or the short movie Sunspring; however, these works used less advanced technology, and either were very short (Sunspring) or necessitated a larger amount of human interventions. The reviewers note that the script is far from perfect, with many inconsistencies and nonsensical parts, and conclude that the technology is definitely not yet ready to replace human authors; however, some find some parts of the script frighteningly human-like. The amount of human intervention is a somewhat controversial topic, with some reviewers finding the human influence too large (especially in interpreting the script and putting the play on scene), while others feel that a greater amount of human intervention would have been favorable as this could greatly improve the quality of the play. The reviews also frequently comment on the amount of sex, violence and strong language in the play; this can be attributed to the method used for creating the script, where the GPT-2 language model reflects topics and language common in the human-written articles on the internet that were used to train the model. Furthermore, some r
Run-time algorithm specialization
In computer science, run-time algorithm specialization is a methodology for creating efficient algorithms for costly computation tasks of certain kinds. The methodology originates in the field of automated theorem proving and, more specifically, in the Vampire theorem prover project. The idea is inspired by the use of partial evaluation in optimising program translation. Many core operations in theorem provers exhibit the following pattern. Suppose that we need to execute some algorithm a l g ( A , B ) {\displaystyle {\mathit {alg}}(A,B)} in a situation where a value of A {\displaystyle A} is fixed for potentially many different values of B {\displaystyle B} . In order to do this efficiently, we can try to find a specialization of a l g {\displaystyle {\mathit {alg}}} for every fixed A {\displaystyle A} , i.e., such an algorithm a l g A {\displaystyle {\mathit {alg}}_{A}} , that executing a l g A ( B ) {\displaystyle {\mathit {alg}}_{A}(B)} is equivalent to executing a l g ( A , B ) {\displaystyle {\mathit {alg}}(A,B)} . The specialized algorithm may be more efficient than the generic one, since it can exploit some particular properties of the fixed value A {\displaystyle A} . Typically, a l g A ( B ) {\displaystyle {\mathit {alg}}_{A}(B)} can avoid some operations that a l g ( A , B ) {\displaystyle {\mathit {alg}}(A,B)} would have to perform, if they are known to be redundant for this particular parameter A {\displaystyle A} . In particular, we can often identify some tests that are true or false for A {\displaystyle A} , unroll loops and recursion, etc. == Difference from partial evaluation == The key difference between run-time specialization and partial evaluation is that the values of A {\displaystyle A} on which a l g {\displaystyle {\mathit {alg}}} is specialised are not known statically, so the specialization takes place at run-time. There is also an important technical difference. Partial evaluation is applied to algorithms explicitly represented as codes in some programming language. At run-time, we do not need any concrete representation of a l g {\displaystyle {\mathit {alg}}} . We only have to imagine a l g {\displaystyle {\mathit {alg}}} when we program the specialization procedure. All we need is a concrete representation of the specialized version a l g A {\displaystyle {\mathit {alg}}_{A}} . This also means that we cannot use any universal methods for specializing algorithms, which is usually the case with partial evaluation. Instead, we have to program a specialization procedure for every particular algorithm a l g {\displaystyle {\mathit {alg}}} . An important advantage of doing so is that we can use some powerful ad hoc tricks exploiting peculiarities of a l g {\displaystyle {\mathit {alg}}} and the representation of A {\displaystyle A} and B {\displaystyle B} , which are beyond the reach of any universal specialization methods. == Specialization with compilation == The specialized algorithm has to be represented in a form that can be interpreted. In many situations, usually when a l g A ( B ) {\displaystyle {\mathit {alg}}_{A}(B)} is to be computed on many values of B {\displaystyle B} in a row, a l g A {\displaystyle {\mathit {alg}}_{A}} can be written as machine code instructions for a special abstract machine, and it is typically said that A {\displaystyle A} is compiled. The code itself can then be additionally optimized by answer-preserving transformations that rely only on the semantics of instructions of the abstract machine. The instructions of the abstract machine can usually be represented as records. One field of such a record, an instruction identifier (or instruction tag), would identify the instruction type, e.g. an integer field may be used, with particular integer values corresponding to particular instructions. Other fields may be used for storing additional parameters of the instruction, e.g. a pointer field may point to another instruction representing a label, if the semantics of the instruction require a jump. All instructions of the code can be stored in a traversable data structure such as an array, linked list, or tree. Interpretation (or execution) proceeds by fetching instructions in some order, identifying their type, and executing the actions associated with said type. In many programming languages, such as C and C++, a simple switch statement may be used to associate actions with different instruction identifiers. Modern compilers usually compile a switch statement with constant (e.g. integer) labels from a narrow range by storing the address of the statement corresponding to a value i {\displaystyle i} in the i {\displaystyle i} -th cell of a special array, as a means of efficient optimisation. This can be exploited by taking values for instruction identifiers from a small interval of values. == Data-and-algorithm specialization == There are situations when many instances of A {\displaystyle A} are intended for long-term storage and the calls of a l g ( A , B ) {\displaystyle {\mathit {alg}}(A,B)} occur with different B {\displaystyle B} in an unpredictable order. For example, we may have to check a l g ( A 1 , B 1 ) {\displaystyle {\mathit {alg}}(A_{1},B_{1})} first, then a l g ( A 2 , B 2 ) {\displaystyle {\mathit {alg}}(A_{2},B_{2})} , then a l g ( A 1 , B 3 ) {\displaystyle {\mathit {alg}}(A_{1},B_{3})} , and so on. In such circumstances, full-scale specialization with compilation may not be suitable due to excessive memory usage. However, we can sometimes find a compact specialized representation A ′ {\displaystyle A^{\prime }} for every A {\displaystyle A} , that can be stored with, or instead of, A {\displaystyle A} . We also define a variant a l g ′ {\displaystyle {\mathit {alg}}^{\prime }} that works on this representation and any call to a l g ( A , B ) {\displaystyle {\mathit {alg}}(A,B)} is replaced by a l g ′ ( A ′ , B ) {\displaystyle {\mathit {alg}}^{\prime }(A^{\prime },B)} , intended to do the same job faster.
You Only Look Once
You Only Look Once (YOLO) is a series of real-time object detection systems based on convolutional neural networks. First introduced by Joseph Redmon et al. in 2015, YOLO has undergone several iterations and improvements, becoming one of the most popular object detection frameworks. The name "You Only Look Once" refers to the fact that the algorithm requires only one forward propagation pass through the neural network to make predictions, unlike previous region proposal-based techniques like R-CNN that require thousands for a single image. == Overview == Compared to previous methods like R-CNN and OverFeat, instead of applying the model to an image at multiple locations and scales, YOLO applies a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities. === OverFeat === OverFeat was an early influential model for simultaneous object classification and localization. Its architecture is as follows: Train a neural network for image classification only ("classification-trained network"). This could be one like the AlexNet. The last layer of the trained network is removed, and for every possible object class, initialize a network module at the last layer ("regression network"). The base network has its parameters frozen. The regression network is trained to predict the ( x , y ) {\displaystyle (x,y)} coordinates of two corners of the object's bounding box. During inference time, the classification-trained network is run over the same image over many different zoom levels and croppings. For each, it outputs a class label and a probability for that class label. Each output is then processed by the regression network of the corresponding class. This results in thousands of bounding boxes with class labels and probability. These boxes are merged until only one single box with a single class label remains. == Versions == There are two parts to the YOLO series. The original part contained YOLOv1, v2, and v3, all released on a website maintained by Joseph Redmon. === YOLOv1 === The original YOLO algorithm, introduced in 2015, divides the image into an S × S {\displaystyle S\times S} grid of cells. If the center of an object's bounding box falls into a grid cell, that cell is said to "contain" that object. Each grid cell predicts B bounding boxes and confidence scores for those boxes. These confidence scores reflect how confident the model is that the box contains an object and how accurate it thinks the box is that it predicts. In more detail, the network performs the same convolutional operation over each of the S 2 {\displaystyle S^{2}} patches. The output of the network on each patch is a tuple as follows: ( p 1 , … , p C , c 1 , x 1 , y 1 , w 1 , h 1 , … , c B , x B , y B , w B , h B ) {\displaystyle (p_{1},\dots ,p_{C},c_{1},x_{1},y_{1},w_{1},h_{1},\dots ,c_{B},x_{B},y_{B},w_{B},h_{B})} where p i {\displaystyle p_{i}} is the conditional probability that the cell contains an object of class i {\displaystyle i} , conditional on the cell containing at least one object. x j , y j , w j , h j {\displaystyle x_{j},y_{j},w_{j},h_{j}} are the center coordinates, width, and height of the j {\displaystyle j} -th predicted bounding box that is centered in the cell. Multiple bounding boxes are predicted to allow each prediction to specialize in one kind of bounding box. For example, slender objects might be predicted by j = 2 {\displaystyle j=2} while stout objects might be predicted by j = 1 {\displaystyle j=1} . c j {\displaystyle c_{j}} is the predicted intersection over union (IoU) of each bounding box with its corresponding ground truth. The network architecture has 24 convolutional layers followed by 2 fully connected layers. During training, for each cell, if it contains a ground truth bounding box, then only the predicted bounding boxes with the highest IoU with the ground truth bounding boxes is used for gradient descent. Concretely, let j {\displaystyle j} be that predicted bounding box, and let i {\displaystyle i} be the ground truth class label, then x j , y j , w j , h j {\displaystyle x_{j},y_{j},w_{j},h_{j}} are trained by gradient descent to approach the ground truth, p i {\displaystyle p_{i}} is trained towards 1 {\displaystyle 1} , other p i ′ {\displaystyle p_{i'}} are trained towards zero. If a cell contains no ground truth, then only c 1 , c 2 , … , c B {\displaystyle c_{1},c_{2},\dots ,c_{B}} are trained by gradient descent to approach zero. === YOLOv2 === Released in 2016, YOLOv2 (also known as YOLO9000) improved upon the original model by incorporating batch normalization, a higher resolution classifier, and using anchor boxes to predict bounding boxes. It could detect over 9000 object categories. It was also released on GitHub under the Apache 2.0 license. === YOLOv3 === YOLOv3, introduced in 2018, contained only "incremental" improvements, including the use of a more complex backbone network, multiple scales for detection, and a more sophisticated loss function. === YOLOv4 and beyond === Subsequent versions of YOLO (v4, v5, etc.) have been developed by different researchers, further improving performance and introducing new features. These versions are not officially associated with the original YOLO authors but build upon their work. As of 2026, versions up to YOLO26 have been released..
Data (word)
The word data is most often used as a singular collective mass noun in educated everyday usage. However, due to the history and etymology of the word, considerable controversy has existed on whether it should be considered a mass noun used with verbs conjugated in the singular, or should be treated as the plural of the now-rarely-used datum. == Usage in English == In one sense, data is the plural form of datum. Datum actually can also be a count noun with the plural datums (see usage in datum article) that can be used with cardinal numbers (e.g., "80 datums"); data (originally a Latin plural) is not used like a normal count noun with cardinal numbers and can be plural with plural determiners such as these and many, or it can be used as a mass noun with a verb in the singular form. Even when a very small quantity of data is referenced (one number, for example), the phrase piece of data is often used, as opposed to datum. The debate over appropriate usage continues, but "data" as a singular form is far more common. In English, the word datum is still used in the general sense of "an item given". In cartography, geography, nuclear magnetic resonance and technical drawing, it is often used to refer to a single specific reference datum from which distances to all other data are measured. Any measurement or result is a datum, though data point is now far more common. Data is indeed most often used as a singular mass noun in educated everyday usage. Some major newspapers, such as The New York Times, use it either in the singular or plural. In The New York Times, the phrases "the survey data are still being analyzed" and "the first year for which data is available" have appeared within one day. The Wall Street Journal explicitly allows this usage in its style guide. The Associated Press style guide classifies data as a collective noun that takes the singular when treated as a unit but the plural when referring to individual items (e.g., "The data is sound" and "The data have been carefully collected"). In scientific writing, data is often treated as a plural, as in These data do not support the conclusions, but the word is also used as a singular mass entity like information (e.g., in computing and related disciplines). British usage now widely accepts treating data as singular in standard English, including everyday newspaper usage at least in non-scientific use. UK scientific publishing still prefers treating it as a plural. Some UK university style guides recommend using data for both singular and plural use, and others recommend treating it only as a singular in connection with computers. The IEEE Computer Society allows usage of data as either a mass noun or plural based on author preference, while IEEE in the editorial style manual indicates to always use the plural form. Some professional organizations and style guides require that authors treat data as a plural noun. For example, the Air Force Flight Test Center once stated that the word data is always plural, never singular.