AI Detector Meme

AI Detector Meme — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Owain Evans

  Owain Rhys Evans is a British artificial intelligence researcher who works on AI alignment and machine learning safety. He founded Truthful AI, a research group based in Berkeley, California, and is an affiliate of the Center for Human Compatible AI (CHAI) at the University of California, Berkeley. His research addresses AI truthfulness, emergent behaviors in large language models, and the alignment of AI systems with human values. == Education == Evans earned a Bachelor of Arts in philosophy and mathematics from Columbia University in 2008 and a PhD in philosophy from the Massachusetts Institute of Technology in 2015. His doctoral research focused on Bayesian computational models of human preferences and decision-making. == Career == After completing his doctorate, Evans held positions at the Future of Humanity Institute (FHI) at the University of Oxford, first as a postdoctoral research fellow and later as a research scientist. While at FHI, he co-authored a survey of machine learning researchers on timelines for human-level AI, published in the Journal of Artificial Intelligence Research. The survey was reported on by Newsweek, New Scientist, the BBC, and The Economist. He was also among the co-authors of a 2018 report on the potential for misuse of AI technologies, published by researchers at Oxford, Cambridge, and other institutions. Since 2022, Evans has been based in Berkeley, where he founded Truthful AI, a non-profit research group that studies AI truthfulness, deception, and emergent behaviors in large language models. == Research == Evans's early work examined challenges in inverse reinforcement learning when human behavior is irrational or biased, proposing methods for AI systems to infer preferences from imperfect human demonstrations. He co-developed TruthfulQA (2021), a benchmark that tests whether language models give truthful answers rather than repeating common misconceptions. Initial evaluations found that larger models were not more truthful, suggesting that scaling alone does not improve factual accuracy. The benchmark has since been used by AI developers to evaluate large language models. He also co-authored a paper proposing design and governance strategies for building AI systems that do not deceive or hallucinate. In 2023, Evans and collaborators described the "reversal curse", showing that language models trained on a fact in one direction (e.g. "A is B") often cannot answer the corresponding reverse query ("B is A"). His group also developed a benchmark for evaluating situational awareness in language models. In 2025, Evans and colleagues published a study in Nature on what they termed "emergent misalignment": fine-tuning a language model on a narrow task (writing insecure code) caused it to produce unrelated harmful outputs without explicit instruction to do so. Later that year, Evans and collaborators (including researchers at Anthropic) reported that hidden behavioral traits can transfer between language models through training data, even when those traits are not explicitly present in the data, a phenomenon they called "subliminal learning". == Public engagement == In November 2025, Evans delivered the Hinton Lectures, a keynote lecture series on AI safety co-founded by Geoffrey Hinton and the Global Risk Institute.

  Read more →
• 

  Image registration

  Image registration is the process of transforming different sets of data into one coordinate system. Data may be multiple photographs, data from different sensors, times, depths, or viewpoints. It is used in computer vision, medical imaging, military automatic target recognition, and compiling and analyzing images and data from satellites. Registration is necessary in order to be able to compare or integrate the data obtained from these different measurements. == Algorithm classification == === Intensity-based vs feature-based === Image registration or image alignment algorithms can be classified into intensity-based and feature-based. One of the images is referred to as the target, fixed or sensed image and the others are referred to as the moving or source images. Image registration involves spatially transforming the source/moving image(s) to align with the target image. The reference frame in the target image is stationary, while the other datasets are transformed to match to the target. Intensity-based methods compare intensity patterns in images via correlation metrics, while feature-based methods find correspondence between image features such as points, lines, and contours. Intensity-based methods register entire images or sub-images. If sub-images are registered, centers of corresponding sub images are treated as corresponding feature points. Feature-based methods establish a correspondence between a number of especially distinct points in images. Knowing the correspondence between a number of points in images, a geometrical transformation is then determined to map the target image to the reference images, thereby establishing point-by-point correspondence between the reference and target images. Methods combining intensity-based and feature-based information have also been developed. === Transformation models === Image registration algorithms can also be classified according to the transformation models they use to relate the target image space to the reference image space. The first broad category of transformation models includes affine transformations, which include rotation, scaling, translation and shearing. Affine transformations are global in nature, thus, they cannot model local geometric differences between images. The second category of transformations allow 'elastic' or 'nonrigid' transformations. These transformations are capable of locally warping the target image to align with the reference image. Nonrigid transformations include radial basis functions (thin-plate or surface splines, multiquadrics, and compactly-supported transformations), physical continuum models (viscous fluids), and large deformation models (diffeomorphisms). Transformations are commonly described by a parametrization, where the model dictates the number of parameters. For instance, the translation of a full image can be described by a translation vector parameter. These models are called parametric models. Non-parametric models on the other hand, do not follow any parameterization, allowing each image element to be displaced arbitrarily. There are a number of programs that implement both estimation and application of a warp-field. It is a part of the SPM and AIR programs. === Transformations of coordinates via the law of function composition rather than addition === Alternatively, many advanced methods for spatial normalization are building on structure preserving transformations homeomorphisms and diffeomorphisms since they carry smooth submanifolds smoothly during transformation. Diffeomorphisms are generated in the modern field of Computational Anatomy based on flows since diffeomorphisms are not additive although they form a group, but a group under the law of function composition. For this reason, flows which generalize the ideas of additive groups allow for generating large deformations that preserve topology, providing 1-1 and onto transformations. Computational methods for generating such transformation are often called LDDMM which provide flows of diffeomorphisms as the main computational tool for connecting coordinate systems corresponding to the geodesic flows of Computational Anatomy. There are a number of programs which generate diffeomorphic transformations of coordinates via diffeomorphic mapping including MRI Studio and MRI Cloud.org === Spatial vs frequency domain methods === Spatial methods operate in the image domain, matching intensity patterns or features in images. Some of the feature matching algorithms are outgrowths of traditional techniques for performing manual image registration, in which an operator chooses corresponding control points (CP) in images. When the number of control points exceeds the minimum required to define the appropriate transformation model, iterative algorithms like RANSAC can be used to robustly estimate the parameters of a particular transformation type (e.g. affine) for registration of the images. Frequency-domain methods find the transformation parameters for registration of the images while working in the transform domain. Such methods work for simple transformations, such as translation, rotation, and scaling. Applying the phase correlation method to a pair of images produces a third image which contains a single peak. The location of this peak corresponds to the relative translation between the images. Unlike many spatial-domain algorithms, the phase correlation method is resilient to noise, occlusions, and other defects typical of medical or satellite images. Additionally, the phase correlation uses the fast Fourier transform to compute the cross-correlation between the two images, generally resulting in large performance gains. The method can be extended to determine rotation and scaling differences between two images by first converting the images to log-polar coordinates. Due to properties of the Fourier transform, the rotation and scaling parameters can be determined in a manner invariant to translation. === Single- vs multi-modality methods === Another classification can be made between single-modality and multi-modality methods. Single-modality methods tend to register images in the same modality acquired by the same scanner/sensor type, while multi-modality registration methods tended to register images acquired by different scanner/sensor types. Multi-modality registration methods are often used in medical imaging as images of a subject are frequently obtained from different scanners. Examples include registration of brain CT/MRI images or whole body PET/CT images for tumor localization, registration of contrast-enhanced CT images against non-contrast-enhanced CT images for segmentation of specific parts of the anatomy, and registration of ultrasound and CT images for prostate localization in radiotherapy. === Automatic vs interactive methods === Registration methods may be classified based on the level of automation they provide. Manual, interactive, semi-automatic, and automatic methods have been developed. Manual methods provide tools to align the images manually. Interactive methods reduce user bias by performing certain key operations automatically while still relying on the user to guide the registration. Semi-automatic methods perform more of the registration steps automatically but depend on the user to verify the correctness of a registration. Automatic methods do not allow any user interaction and perform all registration steps automatically. === Similarity measures for image registration === Image similarities are broadly used in medical imaging. An image similarity measure quantifies the degree of similarity between intensity patterns in two images. The choice of an image similarity measure depends on the modality of the images to be registered. Common examples of image similarity measures include cross-correlation, mutual information, sum of squared intensity differences, and ratio image uniformity. Mutual information and normalized mutual information are the most popular image similarity measures for registration of multimodality images. Cross-correlation, sum of squared intensity differences and ratio image uniformity are commonly used for registration of images in the same modality. Many new features have been derived for cost functions based on matching methods via large deformations have emerged in the field Computational Anatomy including Measure matching which are pointsets or landmarks without correspondence, Curve matching and Surface matching via mathematical currents and varifolds. == Uncertainty == There is a level of uncertainty associated with registering images that have any spatio-temporal differences. A confident registration with a measure of uncertainty is critical for many change detection applications such as medical diagnostics. In remote sensing applications where a digital image pixel may represent several kilometers of spatial distance (such as NASA's LANDSAT imagery), an uncertain image registration can mean that a solution could b

  Read more →
• 

  Colloquis

  Colloquis, previously known as ActiveBuddy and Conversagent, was a company that created conversation-based interactive agents originally distributed via instant messaging platforms. The company had offices in New York, New York, and Sunnyvale, California. == History == Founded in 2000, the company was the brainchild of Robert Hoffer, Timothy Kay, and Peter Levitan. The idea for interactive agents (also known as Internet bots) came from the team's vision to add functionality to increasingly popular instant messaging services. The original implementation took shape as a word-based adventure game but quickly grew to include a wide range of database applications, including access to news, weather, stock information, movie times, Yellow Pages listings, and detailed sports data, as well as a variety of tools (calculators, translator, etc.). These various applications were bundled into one entity and launched as SmarterChild in 2001. SmarterChild acted as a showcase for the quick data access and possibilities for fun conversation that the company planned to turn into customized, niche-specific products. The rapid success of SmarterChild led to targeted promotional products for Radiohead, Austin Powers, The Sporting News, and others. ActiveBuddy sought to strengthen its hold on the interactive agent market for the future by filing for, and receiving, a controversial patent on their creation in 2002. The company also released the BuddyScript SDK, a free developer kit that allow programmers to design and launch their own interactive agents using ActiveBuddy's proprietary scripting language, in 2002. Ultimately, however, the decline in ad spending in 2001 and 2002 led to a shift in corporate strategy towards business focused Automated Service Agents, building products for clients including Cingular, Comcast and Cox Communications. The company subsequently changed its name from ActiveBuddy to Conversagent in 2003, and then again to Colloquis in 2006. Colloquis was purchased by Microsoft in October 2006.

  Read more →
• 

  Microsoft Teams

  Microsoft Teams is a team collaboration platform developed by Microsoft as part of the Microsoft 365 suite. It offers features such as workspace chat, video conferencing, file storage, and integration with both Microsoft and third-party applications and services. Teams gradually replaced earlier Microsoft messaging and collaboration platforms, including Skype for Business, Skype, Flip, and Microsoft Classroom. The platform saw significant growth during the COVID-19 pandemic, alongside competitors such as Zoom, Slack, and Google Meet, as organizations shifted to remote work and virtual meetings. As of January 2023, Microsoft reported approximately 280 million monthly active users. == History == On August 29, 2007, Microsoft acquired Parlano, the developer of the persistent group chat tool MindAlign. Years later, on March 4, 2016, Microsoft considered acquiring Slack for $8 billion. However, the proposal was reportedly opposed by Bill Gates, who advocated for focusing on enhancing Skype for Business instead. Lu Qi, then executive vice president of Applications and Services, had led the initiative to pursue the Slack acquisition. Following Lu's departure later that year, Microsoft announced Microsoft Teams on November 2, 2016, at an event in New York City, positioning it as a direct competitor to Slack. Teams launched worldwide on March 14, 2017. The service was initially led by corporate vice president Brian MacDonald. In response to the launch, Slack published a full-page advertisement in The New York Times welcoming the competition and outlining its product philosophy. Although Slack was used by 28 companies in the Fortune 100, The Verge wrote that executives would question paying for the service if Teams provides a similar function in their company's existing Office 365 subscription. However, ZDNET noted that the platforms initially served different markets, as Teams did not support external users, making it less appealing to small businesses and freelancers, a limitation Microsoft later addressed. In response to Teams' announcement, Slack deepened in-product integration with Google services. In May 2017, Microsoft announced that Teams would replace Microsoft Classroom in Office 365 Education. A free version of Teams was released on July 12, 2018, offering most core features at no cost, albeit with limits on users and storage. In January 2019, Microsoft introduced updates targeting "Firstline Workers" to improve Teams’ performance across shared or limited-access devices. In September 2019, Microsoft announced the retirement of Skype for Business in favor of Teams, which took effect on July 31, 2021. In early 2020, Microsoft introduced a push-to-talk "Walkie Talkie" feature aimed at firstline workers using smartphones and tablets over Wi-Fi or cellular networks. The COVID-19 pandemic significantly boosted usage of Teams. On March 19, 2020, Microsoft reported 44 million daily active users. In April, the platform logged 4.1 billion meeting minutes in a single day. A public preview of Microsoft Teams for Linux was released in December 2019, but the Linux client was discontinued in 2022. In July 2020, Microsoft shut down its video game livestreaming platform Mixer, and announced that some of its technologies would be repurposed for use in Teams. On February 28, 2025, Microsoft announced that Skype would be fully retired on May 5, 2025, with users given options to export their data or transition to Microsoft Teams. In October 2025, together with other Microsoft 365 suite apps, Teams had its logo updated. == Usage == == Underlying software == Microsoft Teams, as part of the Microsoft 365 suite, utilizes SharePoint and Exchange Online. Each Team, Shared Channel, and Private Channel has its own Microsoft 365 Group and SharePoint Site used for file storage. Messages are stored in Cosmos DB and are journaled to Exchange Online mailboxes. Private messages, including messages in Private Channels, are journaled to the sender and recipients' mailboxes. Public Channel messages are journaled to their corresponding Team's group mailbox, whereas, messages from Shared Channels are journaled to their own mailboxes. Contacts and voicemail are stored in Exchange Online. Microsoft Teams client is a web-based desktop app, originally developed on top of the Electron framework which combines the Chromium rendering engine and the Node.js JavaScript platform. Version 2.0 client was rebuilt using the Evergreen version of Microsoft Edge WebView2 in place of Electron. == Features == === Chats === Teams allows users to communicate in two-way persistent chats with one or multiple participants. Participants can message using text, emojis, stickers and gifs, as well as sharing links and files. In August 2022, the chat feature was updated for "chat with yourself"; allowing for the organization of files, notes, comments, images, and videos within a private chat tab. === Teams === Teams allows communities, groups, or teams to contribute in a shared workspace where messages and digital content on a specific topic are shared. Team members can join through an invitation sent by a team administrator or owner or sharing of a specific URL. Teams for Education allows admins and teachers to set up groups for classes, professional learning communities (PLCs), staff members, and everyone. === Channels === Channels allow team members to communicate without the use of email or group SMS (texting). Users can reply to posts with text, images, GIFs, and image macros. Direct messages send private messages to designated users rather than the entire channel. Connectors can be used within a channel to submit information contacted through a third-party service. Connectors include Mailchimp, Facebook Pages, Twitter, Power BI and Bing News. === Group conversations === Ad-hoc groups can be created to share instant messaging, audio calls (VoIP), and video calls inside the client software. === Telephone replacement === A feature on one of the higher cost licencing tiers allows connectivity to the public switched telephone network (PSTN) telephone system. This allows users to use Teams as if it were a telephone, making and receiving calls over the PSTN, including the ability to host "conference calls" with multiple participants. === Meeting === Meetings can be scheduled with multiple participants able to share audio, video, chat and presented content with all participants. Multiple users can connect via a meeting link. Automated minutes are possible using the recording and transcript features. Teams has a plugin for Microsoft Outlook to schedule a Teams Meeting in Outlook for a specific date and time and invite others to attend. If a meeting is scheduled within a channel, users visiting the channel are able to see if a meeting is in progress. ==== Teams Live Events ==== Teams Live Events replaces Skype Meeting Broadcast for users to broadcast to 10,000 participants on Teams, Yammer, or Microsoft Stream. ==== Breakout Rooms ==== Breakout rooms split a meeting into small groups. This is often utilized for collaboration during trainings or any environment where having all participants speak at once could be disruptive or unfeasible. Breakout rooms can be set by the hosts to a certain length of time, after which all participants will automatically rejoin the main meeting room. ==== Front Row ==== Front Row adjusts the layout of the viewer's screen, placing the speaker or content in the center of the gallery with other meeting participant's video feeds reduced in size and located below the speaker. === Education === Microsoft Teams for Education allows teachers to distribute, provide feedback, and grade student assignments turned in via Teams using the Assignments tab through Office 365 for Education subscribers. Quizzes can also be assigned to students through an integration with Office Forms. === Protocols === Microsoft Teams is based on a number of Microsoft-specific protocols. Video conferences are realized over the protocol MNP24, known from the Skype consumer version. VoIP and video conference clients based on SIP and H.323 need special gateways to connect to Microsoft Teams servers. With the help of Interactive Connectivity Establishment (ICE), clients behind Network address translation routers and restrictive firewalls are also able to connect, if peer-to-peer is not possible. === Integrations === Microsoft Teams has integrations through Microsoft AppSource, its integration marketplace. In 2020, Microsoft partnered with KUDO, a cloud-based solution with language interpretation, to allow integrated language meeting controls. In June 2022, an update was released using AI to improve call audio through the elimination of background feedback loops and cancelling non-vocal audio. == Anti-trust controversy == In July 2023, the European Commission opened an anti-trust investigation into the possibility that Microsoft unfairly used its office suite market power to increase sales of Teams and hurt

  Read more →
• 

  Landweber iteration

  The Landweber iteration or Landweber algorithm is an algorithm to solve ill-posed linear inverse problems, and it has been extended to solve non-linear problems that involve constraints. The method was first proposed in the 1950s by Louis Landweber, and it can be now viewed as a special case of many other more general methods. == Basic algorithm == The original Landweber algorithm attempts to recover a signal x from (noisy) measurements y. The linear version assumes that y = A x {\displaystyle y=Ax} for a linear operator A. When the problem is in finite dimensions, A is just a matrix. When A is nonsingular, then an explicit solution is x = A − 1 y {\displaystyle x=A^{-1}y} . However, if A is ill-conditioned, the explicit solution is a poor choice since it is sensitive to any noise in the data y. If A is singular, this explicit solution doesn't even exist. The Landweber algorithm is an attempt to regularize the problem, and is one of the alternatives to Tikhonov regularization. We may view the Landweber algorithm as solving: min x ‖ A x − y ‖ 2 2 / 2 {\displaystyle \min _{x}\|Ax-y\|_{2}^{2}/2} using an iterative method. The algorithm is given by the update x k + 1 = x k − ω A ∗ ( A x k − y ) . {\displaystyle x_{k+1}=x_{k}-\omega A^{}(Ax_{k}-y).} where the relaxation factor ω {\displaystyle \omega } satisfies 0 < ω < 2 / σ 1 2 {\displaystyle 0<\omega <2/\sigma _{1}^{2}} . Here σ 1 {\displaystyle \sigma _{1}} is the largest singular value of A {\displaystyle A} . If we write f ( x ) = ‖ A x − y ‖ 2 2 / 2 {\displaystyle f(x)=\|Ax-y\|_{2}^{2}/2} , then the update can be written in terms of the gradient x k + 1 = x k − ω ∇ f ( x k ) {\displaystyle x_{k+1}=x_{k}-\omega \nabla f(x_{k})} and hence the algorithm is a special case of gradient descent. For ill-posed problems, the iterative method needs to be stopped at a suitable iteration index, because it semi-converges. This means that the iterates approach a regularized solution during the first iterations, but become unstable in further iterations. The reciprocal of the iteration index 1 / k {\displaystyle 1/k} acts as a regularization parameter. A suitable parameter is found, when the mismatch ‖ A x k − y ‖ 2 2 {\displaystyle \|Ax_{k}-y\|_{2}^{2}} approaches the noise level. Using the Landweber iteration as a regularization algorithm has been discussed in the literature. == Nonlinear extension == In general, the updates generated by x k + 1 = x k − τ ∇ f ( x k ) {\displaystyle x_{k+1}=x_{k}-\tau \nabla f(x_{k})} will generate a sequence f ( x k ) {\displaystyle f(x_{k})} that converges to a minimizer of f whenever f is convex and the stepsize τ {\displaystyle \tau } is chosen such that 0 < τ < 2 / ( ‖ ∇ f ‖ 2 ) {\displaystyle 0<\tau <2/(\|\nabla f\|^{2})} where ‖ ⋅ ‖ {\displaystyle \|\cdot \|} is the spectral norm. Since this is special type of gradient descent, there currently is not much benefit to analyzing it on its own as the nonlinear Landweber, but such analysis was performed historically by many communities not aware of unifying frameworks. The nonlinear Landweber problem has been studied in many papers in many communities; see, for example. == Extension to constrained problems == If f is a convex function and C is a convex set, then the problem min x ∈ C f ( x ) {\displaystyle \min _{x\in C}f(x)} can be solved by the constrained, nonlinear Landweber iteration, given by: x k + 1 = P C ( x k − τ ∇ f ( x k ) ) {\displaystyle x_{k+1}={\mathcal {P}}_{C}(x_{k}-\tau \nabla f(x_{k}))} where P {\displaystyle {\mathcal {P}}} is the projection onto the set C. Convergence is guaranteed when 0 < τ < 2 / ( ‖ A ‖ 2 ) {\displaystyle 0<\tau <2/(\|A\|^{2})} . This is again a special case of projected gradient descent (which is a special case of the forward–backward algorithm) as discussed in. == Applications == Since the method has been around since the 1950s, it has been adopted and rediscovered by many scientific communities, especially those studying ill-posed problems. In X-ray computed tomography it is called simultaneous iterative reconstruction technique (SIRT). It has also been used in the computer vision community and the signal restoration community. It is also used in image processing, since many image problems, such as deconvolution, are ill-posed. Variants of this method have been used also in sparse approximation problems and compressed sensing settings.

  Read more →
• 

  Celia (virtual assistant)

  Celia is an artificially intelligent virtual assistant developed by Huawei for their latest HarmonyOS and Android-based EMUI smartphones that lack Google Services and a Google Assistant. The assistant can perform day-to-day tasks, which include making a phone call, setting a reminder and checking the weather. It was unveiled on 7 April 2020 and got publicly released on 27 April 2020 via an OTA update solely to selected devices that can update their software to EMUI 10.1. Huawei had initially referred to the new assistant in late 2019 by having announced that there would be an English version of their already 2018 Chinese speaker assistant—Xiaoyi—to be released into the European markets. Due to the on-going China–United States trade war, the company's newly released smartphones were left without any Google services, including the loss of Google Assistant. This subsequently led to the development and release of Celia. AI technology is integrated into the software of Celia, which allows it to translate text using a phones camera and to identify everyday objects — similar to that of Google Lens. == Features == Celia has many features that are similar to that of its rivals: the Google Assistant and Siri. It can be triggered by the words, 'Hey Celia' or be summoned by pressing and holding down on the power button. The default search engine for Celia is Bing, but this can be changed in settings. Celia can make calls, check the agenda, send a message, show the weather, set alarms and control home appliances. The assistant also has the ability to integrate itself with the stock apps of the EMUI software and toggle with the device's settings, such as by turning on the flashlight and playing multimedia content, but with the users command. With the AI that is installed in Celia, it can identify food, everyday objects and translate text using the phones camera. In China, Chinese Xiaoyi packs with an LLM model called PanGu-Σ 3.0 AI on HarmonyOS 4.0 major upgrade improvements from Celia, making the assistant smarter and more advanced compared to when it was launched in 2020 on EMUI handsets in China and internationally, surpassing Apple and Google by the being the first in the AI industry, with a dedicated AI system framework of APIs on the latest operating system that evolves to a complete large dedicated AI software stack called Harmony Intelligence of Pangu Embedded variant model and MindSpore AI framework with Neural Network Runtime on OpenHarmony-based HarmonyOS NEXT base system to replace the dual framework system with a single frame HarmonyOS 5.0 version by Q4 2024, first introduced on June 21, 2024, in Developer Beta 1 preview release at HDC 2024. == Availability by country and language == Currently, Celia is available only in German, English, French and Spanish, and has been released in Germany, the UK, France, Spain, Chile, Mexico and Colombia. Huawei has said, that there will be more regions and languages to come. == Compatible devices == Celia only became available with the EMUI 10.1 update that was released in April, which means that a limited number of devices are compatible with it. More devices will be added to the list throughout the coming months as Celia's availability increases. The current list is shown below: === Huawei P series === Huawei P50 (Pro) Huawei P40 (Lite, Pro & Pro+) Huawei P30 (Pro) === Huawei Mate series === Huawei Mate 40 Huawei Mate 30 (Lite, Pro & RS Porche Design) Huawei MatePad Pro Huawei Mate 20 (Pro, 20X 4G, 20X 5G and RS Porche Design) Huawei Mate X & Xs === Huawei Nova series === Huawei Nova 6 (Nova 6 5G & Nova 6 SE) Huawei Nova 5 (Nova 5 Pro, Nova 5i Pro & Nova 5Z) Huawei Nova Y60 === Huawei Enjoy series === Huawei Enjoy 10S == Issues == Technology news website Engadget has noted that when saying, 'Hey Celia', out aloud in the presence of an iPhone, Siri will respond along with Celia; this is apparently because 'Celia' sounds similar to 'Siri'.

  Read more →
• 

  AsoSoft text corpus

  The AsoSoft text corpus is the first large-scale Kurdish text corpus, collected and processed by the AsoSoft research and development group. It contains 458,000 documents (188 million tokens) that are collected from sources such as websites, news agencies, books, and magazines. The corpus is partially tagged by topic, so it can be used for topic identification tasks. Also, it is applicable for extracting language model and computational lexicon information. Part of the corpus (75 million tokens) is available online for non-commercial use. The corpus uses the TEI format.

  Read more →
• 

  History of natural language processing

  The history of natural language processing describes the advances of natural language processing. There is some overlap with the history of machine translation, the history of speech recognition, and the history of artificial intelligence. == Early history == The history of machine translation dates back to the seventeenth century, when philosophers such as Leibniz and Descartes put forward proposals for codes which would relate words between languages. All of these proposals remained theoretical, and none resulted in the development of an actual machine. The first patents for "translating machines" were applied for in the mid-1930s. One proposal, by Georges Artsrouni, was simply an automatic bilingual dictionary using paper tape. The other proposal, by Peter Troyanskii, a Russian, was more detailed. Troyanskii’s proposal included both the bilingual dictionary and a method for dealing with grammatical roles between languages, based on Esperanto. == Logical period == In 1950, Alan Turing published his famous article "Computing Machinery and Intelligence" which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably — on the basis of the conversational content alone — between the program and a real human. In 1957, Noam Chomsky’s Syntactic Structures revolutionized Linguistics with 'universal grammar', a rule-based system of syntactic structures. The Georgetown experiment in 1954 involved fully automatic translation of more than sixty Russian sentences into English. The authors claimed that within three or five years, machine translation would be a solved problem. However, real progress was much slower, and after the ALPAC report in 1966, which found that ten years long research had failed to fulfill the expectations, funding for machine translation was dramatically reduced. Little further research in machine translation was conducted until the late 1980s, when the first statistical machine translation systems were developed. Some notably successful NLP systems developed in the 1960s were SHRDLU, a natural language system working in restricted "blocks worlds" with restricted vocabularies. In 1969 Roger Schank introduced the conceptual dependency theory for natural language understanding. This model, partially influenced by the work of Sydney Lamb, was extensively used by Schank's students at Yale University, such as Robert Wilensky, Wendy Lehnert, and Janet Kolodner. In 1970, William A. Woods introduced the augmented transition network (ATN) to represent natural language input. Instead of phrase structure rules ATNs used an equivalent set of finite-state automata that were called recursively. ATNs and their more general format called "generalized ATNs" continued to be used for a number of years. During the 1970s many programmers began to write 'conceptual ontologies', which structured real-world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, many chatterbots were written including PARRY, Racter, and Jabberwacky. == Statistical period == Up to the 1980s, most NLP systems were based on complex sets of hand-written rules. Starting in the late 1980s, however, there was a revolution in NLP with the introduction of machine learning algorithms for language processing. This was due both to the steady increase in computational power resulting from Moore's law and the gradual lessening of the dominance of Chomskyan theories of linguistics (e.g. transformational grammar), whose theoretical underpinnings discouraged the sort of corpus linguistics that underlies the machine-learning approach to language processing. Some of the earliest-used machine learning algorithms, such as decision trees, produced systems of hard if-then rules similar to existing hand-written rules. Increasingly, however, research has focused on statistical models, which make soft, probabilistic decisions based on attaching real-valued weights to the features making up the input data. The cache language models upon which many speech recognition systems now rely are examples of such statistical models. Such models are generally more robust when given unfamiliar input, especially input that contains errors (as is very common for real-world data), and produce more reliable results when integrated into a larger system comprising multiple subtasks. === Datasets === The emergence of statistical approaches was aided by both increase in computing power and the availability of large datasets. At that time, large multilingual corpora were starting to emerge. Notably, some were produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government. Many of the notable early successes occurred in the field of machine translation. In 1993, the IBM alignment models were used for statistical machine translation. Compared to previous machine translation systems, which were symbolic systems manually coded by computational linguists, these systems were statistical, which allowed them to automatically learn from large textual corpora. Though these systems do not work well in situations where only small corpora is available, so data-efficient methods continue to be an area of research and development. In 2001, a one-billion-word large text corpus, scraped from the Internet, referred to as "very very large" at the time, was used for word disambiguation. To take advantage of large, unlabelled datasets, algorithms were developed for unsupervised and self-supervised learning. Generally, this task is much more difficult than supervised learning, and typically produces less accurate results for a given amount of input data. However, there is an enormous amount of non-annotated data available (including, among other things, the entire content of the World Wide Web), which can often make up for the inferior results. == Neural period == Neural language models were developed in 1990s. In 1990, the Elman network, using a recurrent neural network, encoded each word in a training set as a vector, called a word embedding, and the whole vocabulary as a vector database, allowing it to perform such tasks as sequence-predictions that are beyond the power of a simple multilayer perceptron. A shortcoming of the static embeddings was that they didn't differentiate between multiple meanings of homonyms. Yoshua Bengio developed the first neural probabilistic language model in 2000. Novel algorithms, availability of larger datasets and higher processing power made possible training of larger and larger language models. Attention mechanism was introduced by Bahdanau et al. in 2014. This work laid the foundations for the famous "Attention Is All You Need" paper that introduced the Transformer architecture in 2017. The concept of large language model (LLM) emerged in late 2010s. LLM is a language model trained with self-supervised learning on vast amount of text. Earliest public LLMs had hundreds of millions of parameters, but this number quickly rose to billion and even trillions. In recent years, advancements in deep learning and large language models have significantly enhanced the capabilities of natural language processing, leading to widespread applications in areas such as healthcare, customer service, and content generation. == Software ==

  Read more →
• 

  Rapid prototyping

  Rapid prototyping is a group of techniques used to quickly fabricate a scale model of a physical part or assembly using three-dimensional computer aided design (CAD) data. Construction of the part or assembly is usually done using 3D printing or "additive layer manufacturing" technology. The first methods for rapid prototyping became available in mid 1987 and were used to produce models and prototype parts. Today, they are used for a wide range of applications and are used to manufacture production-quality parts in relatively small numbers if desired without the typical unfavorable short-run economics. This economy has encouraged online service bureaus. Historical surveys of RP technology start with discussions of simulacra production techniques used by 19th-century sculptors. Some modern sculptors use the progeny technology to produce exhibitions and various objects. The ability to reproduce designs from a dataset has given rise to issues of rights, as it is now possible to interpolate volumetric data from 2D images. As with CNC subtractive methods, the computer-aided-design – computer-aided manufacturing CAD -CAM workflow in the traditional rapid prototyping process starts with the creation of geometric data, either as a 3D solid using a CAD workstation, or 2D slices using a scanning device. For rapid prototyping this data must represent a valid geometric model; namely, one whose boundary surfaces enclose a finite volume, contain no holes exposing the interior, and do not fold back on themselves. In other words, the object must have an "inside". The model is valid if for each point in 3D space the computer can determine uniquely whether that point lies inside, on, or outside the boundary surface of the model. CAD post-processors will approximate the application vendors' internal CAD geometric forms (e.g., B-splines) with a simplified mathematical form, which in turn is expressed in a specified data format which is a common feature in additive manufacturing: STL file format, a de facto standard for transferring solid geometric models to SFF machines. To obtain the necessary motion control trajectories to drive the actual SFF, rapid prototyping, 3D printing or additive manufacturing mechanism, the prepared geometric model is typically sliced into layers, and the slices are scanned into lines (producing a "2D drawing" used to generate trajectory as in CNC's toolpath), mimicking in reverse the layer-to-layer physical building process. == Application areas == Rapid prototyping is also commonly applied in software engineering to try out new business models and application architectures such as Aerospace, Automotive, Financial Services, Product development, and Healthcare. Aerospace design and industrial teams rely on prototyping in order to create new AM methodologies in the industry. Using SLA they can quickly make multiple versions of their projects in a few days and begin testing quicker. Rapid Prototyping allows designers/developers to provide an accurate idea of how the finished product will turn out before putting too much time and money into the prototype. 3D printing being used for Rapid Prototyping allows for Industrial 3D printing to take place. With this, you could have large-scale moulds to spare parts being pumped out quickly within a short period of time. == Types of Rapid Prototyping == Stereolithography (SLA) → a laser-cured photopolymer for materials such as thermoplastic-like photopolymers. Selective Laser Sintering (SLS) → a laser-sintered powder for materials such as Nylon or TPU. Direct Metal Laser Sintering (DMLS) → laser-sintered metal powder for materials like stainless steel, titanium, chrome, and aluminum. Fused Deposition Modeling (FDM) → fused extrusions of filaments like ABS, PC, and PPCU. Multi Jet Fusion (MJF) → it is an inkjet array selective fusing across bed of nylon powder for Black Nylon 12. PolyJet (PJET) → it is a uv-cured jetted photopolymer to work with acrylic-based and elastomeric photopolymers. Computer Numerical Controlled Machine (CNC) → it is used for manipulating engineering-grade thermoplastics and metals. Injection Molding (IM) → the injection is done using aluminum molds and it is used for thermoplastics, metals and liquid silicone rubber. Vacuum Casting→ is a manufacturing process used to create high-quality prototypes and small batches of parts. == History == In the 1970s, Joseph Henry Condon and others at Bell Labs developed the Unix Circuit Design System (UCDS), automating the laborious and error-prone task of manually converting drawings to fabricate circuit boards for the purposes of research and development. By the 1980s, U.S. policy makers and industrial managers were forced to take note that America's dominance in the field of machine tool manufacturing evaporated, in what was named the machine tool crisis. Numerous projects sought to counter these trends in the traditional CNC CAM area, which had begun in the US. Later when Rapid Prototyping Systems moved out of labs to be commercialized, it was recognized that developments were already international and U.S. rapid prototyping companies would not have the luxury of letting a lead slip away. The National Science Foundation was an umbrella for the National Aeronautics and Space Administration (NASA), the US Department of Energy, the US Department of Commerce NIST, the US Department of Defense, Defense Advanced Research Projects Agency (DARPA), and the Office of Naval Research coordinated studies to inform strategic planners in their deliberations. One such report was the 1997 Rapid Prototyping in Europe and Japan Panel Report in which Joseph J. Beaman founder of DTM Corporation [DTM RapidTool pictured] provides a historical perspective: The roots of rapid prototyping technology can be traced to practices in topography and photosculpture. Within TOPOGRAPHY Blanther (1892) suggested a layered method for making a mold for raised relief paper topographical maps .The process involved cutting the contour lines on a series of plates which were then stacked. Matsubara (1974) of Mitsubishi proposed a topographical process with a photo-hardening photopolymer resin to form thin layers stacked to make a casting mold. PHOTOSCULPTURE was a 19th-century technique to create exact three-dimensional replicas of objects. Most famously Francois Willeme (1860) placed 24 cameras in a circular array and simultaneously photographed an object. The silhouette of each photograph was then used to carve a replica. Morioka (1935, 1944) developed a hybrid photo sculpture and topographic process using structured light to photographically create contour lines of an object. The lines could then be developed into sheets and cut and stacked, or projected onto stock material for carving. The Munz (1956) Process reproduced a three-dimensional image of an object by selectively exposing, layer by layer, a photo emulsion on a lowering piston. After fixing, a solid transparent cylinder contains an image of the object. "The Origins of Rapid Prototyping - RP stems from the ever-growing CAD industry, more specifically, the solid modeling side of CAD. Before solid modeling was introduced in the late 1980's, three-dimensional models were created with wire frames and surfaces. But not until the development of true solid modeling could innovative processes such as RP be developed. Charles Hull, who helped found 3D Systems in 1986, developed the first RP process. This process, called stereolithography, builds objects by curing thin consecutive layers of certain ultraviolet light-sensitive liquid resins with a low-power laser. With the introduction of RP, CAD solid models could suddenly come to life". The technologies referred to as Solid Freeform Fabrication are what we recognize today as rapid prototyping, 3D printing or additive manufacturing: Swainson (1977), Schwerzel (1984) worked on polymerization of a photosensitive polymer at the intersection of two computer controlled laser beams. Ciraud (1972) considered magnetostatic or electrostatic deposition with electron beam, laser or plasma for sintered surface cladding. These were all proposed but it is unknown if working machines were built. Hideo Kodama of Nagoya Municipal Industrial Research Institute was the first to publish an account of a solid model fabricated using a photopolymer rapid prototyping system (1981). The first 3D rapid prototyping system relying on Fused Deposition Modeling (FDM) was made in April 1992 by Stratasys but the patent did not issue until June 9, 1992. Sanders Prototype, Inc introduced the first desktop inkjet 3D Printer (3DP) using an invention from August 4, 1992 (Helinski), Modelmaker 6Pro in late 1993 and then the larger industrial 3D printer, Modelmaker 2, in 1997. Z-Corp using the MIT 3DP powder binding for Direct Shell Casting (DSP) invented 1993 was introduced to the market in 1995. Even at that early date the technology was seen as having a place in manufacturing practice. A low resol

  Read more →
• 

  Meta AI

  Meta AI is a research division of Meta (formerly Facebook) that develops artificial intelligence and augmented reality technologies. == History == Meta AI was founded in 2013 as Facebook Artificial Intelligence Research (FAIR). It has workspaces in Menlo Park, London, New York City, Paris, Seattle, Pittsburgh, Tel Aviv, and Montreal as of 2025. In 2016, FAIR partnered with Google, Amazon, IBM, and Microsoft in creating the Partnership on Artificial Intelligence to Benefit People and Society. Meta AI was directed by Yann LeCun until 2018, when Jérôme Pesenti succeeded the role. Pesenti is formerly the CTO of IBM's big data group. FAIR's research includes self-supervised learning, generative adversarial networks, document classification and translation, and computer vision. FAIR released Torch deep-learning modules as well as PyTorch in 2017, an open-source machine learning framework, which was subsequently used in several deep learning technologies, such as Tesla's autopilot and Uber's Pyro. That same year, a pair of chatbots were falsely rumored to be discontinued for developing a language that was unintelligible to humans. FAIR clarified that the research had been shut down because they had accomplished their initial goal to understand how languages are generated by their models, rather than out of fear. FAIR was renamed Meta AI following the rebranding that changed Facebook, Inc. to Meta Platforms Inc. On October 1, 2025, Facebook announced "We will soon use your interactions with AI at Meta to personalize the content and ads you see". == Virtual assistant == Meta AI is also the name of the virtual assistant developed by the team, now integrated as a chatbot into Meta's social networking products. It is also available as a subscription-based stand-alone app. The virtual assistant was pre-installed on the second generation of Ray-Ban Meta smartglasses, and can incorporate inputs from the glasses' cameras after an update. It is also available on Quest 2 and newer HMDs. Since May 2024, the chatbot has summarized news from various outlets without linking directly to original articles, including in Canada, where news links are banned on its platforms. This use of news content without compensation and attribution has raised ethical and legal concerns, especially as Meta continues to reduce news visibility on its platforms. == Current research == === Natural language processing and chatbot === Natural language processing is the ability for machines to understand and generate natural language. The team is also researching unsupervised machine translation and multilingual chatbots. ==== Galactica ==== Galactica is a large language model (LLM) designed for generating scientific text. It was available for three days from 15 November 2022, before being withdrawn for generating racist and inaccurate content. ==== Llama ==== Llama is an LLM released in February 2023. As of January 2026, the most recent release is the Llama 4. === Hardware === Meta used CPUs and in-house custom chips before 2022; they switched to Nvidia GPUs since then. MTIA v1, one of their early chips, is designed for the company's content recommendation algorithms. It was fabricated on TSMC's 7 nm process technology and consumed 25W, capable of 51.2 TFlops FP16. == Controversy == The French media outlet Mediapart reports that in 2022, Facebook's parent company illegally used works accumulated by the pirate site LibGen to train its artificial intelligence.

  Read more →
• 

  KidDesk

  KidDesk is an alternative desktop software application. The early childhood learning company Hatch Early Childhood created KidDesk; it subsequently went to Edmark, which was bought by IBM then sold to Riverdeep (now Houghton Mifflin Harcourt Learning Technology). KidDesk is compatible with Microsoft Windows 95 and newer, as well as Apple System 7 and newer. KidDesk can be set to start when the computer starts up, and can only be exited through password entry. Adults choose what programs are included for the child to use, what icon represented the desk, and customize the software programs available for use. == History == Edmark first started shipping KidDesk in 1992. In 1993, Edmark updated KidDesk with KidDesk Family Edition for Macintosh and DOS, adding more desk accessories and desk styles (Sometimes included as a free exclusive offer with the Early Learning House and Thinkin' Things Series). In 1995, KidDesk Family Edition was enhanced for Windows 95, and released one month after the new operating system shipped. In 1998, Edmark developed KidDesk Internet Safe. The Internet Safe edition was written for Windows 95, Windows 98, and Macintosh (including OS8). In 2008, HMH ported KidDesk Family Edition was to run on Windows Vista and in 2011 version 3.07 of KidDesk Family Edition was released as part of the 'Young Explorer' suite which is fully supported on Windows XP, Windows Vista and Windows 7. == Features == A picture editor incorporated into the desk. Used both in the Adult settings menu and in the desk itself. KidDesk users can edit their user logo with a pixel grid paint program. A calendar incorporated into the desk. This allows the user to set dates that the user finds important, and allows the date to be marked with a picture or text. A password exit feature. For security reasons, the adult can set a password so that KidDesk can only be exited if it is entered. As an extra security measure, the password exit function could only be accessed if the user pressed the ctrl + alt + A keyboard buttons simultaneously. A skin changer with several themes - farm, princess, sports, ocean, etc. These themes can be changed. The e-mail and voicemail features are customizable depending on the KidDesk installation. The ability to add websites that can be accessed on KidDesk, and the ability to block hyperlinks, JavaScript, data entry, etc., on said sites was an added for the 'Internet Safe' edition released in 1998. KidDesk Internet Safe edition is available in Spanish and Brazilian-Portuguese versions. == Reception == KidDesk was given a platinum award at the 1994 Oppenheim Toy Portfolio Awards. The judges praised the program's security features allowing "configur[ation] so that kids never have access to the possibly destructive DOS prompt", and concluded that "[i]f you and your kids share a computer, you need to install Kiddesk immediately!" === Awards === Since 1992, KidDesk has won 15 major awards.

  Read more →
• 

  Ogle app

  Ogle is a free smartphone based social media application. It is available for iOS and Android. Ogle acts like a school wide forum that lets users and users' classmates share and interact. Users can share photos, videos, questions, even thoughts and watch submissions grow in popularity as other users vote and comment on them. == App Features == Campus Feed: Interact by watching and posting videos or pictures to your campus story. Photos and Videos: share what you want with many different timing options. Interact: Chat with friends and groups, or share a moment for all to see. Real-name system: choose to register an account with username and profile picture. Custom Stickers: Create stickers to add creativity and zest to your pictures. Flash Interaction: All private chat and group chat history will be deleted after 24 hours on Ogle Chat. == Controversies == Users can post anything on Ogle using text, photos, and videos. As a result, some Ogle user's sense of anonymity, posts have targeted specific schools and students with abusive and hurtful content. The Ogle app's user anonymity makes it difficult for school officials to quickly investigate issues that occur within the Ogle app. On March 28, 2016, three people were arrested after violent threats were made against an Anaheim high school. 18-year-old Miguel Meza was arrested Sunday afternoon during a traffic stop, along with his passenger, 23-year-old Johnny Aguilar. Police said both men had loaded handguns. Aguilar was also accused of violating his probation. "It is concerning the fact that they did have firearms, but we don't have a crystal ball. We can't determine if they possessed those firearms to engage in some kind of school violence or if they had it for another reason," Sgt. Daron Wyatt with the Anaheim Police Department said. Officials said Meza and Aguilar have known gang ties and detectives began investigating Meza after threats were made against the school on Ogle. On February 29, 2016, Santa Cruz County sheriff's deputies arrested a 16-year-old Aptos High School student Friday, accused of making an online threat of gun violence at Aptos High and Monte Vista Christian."He basically told detectives that it was all a joke. It's not a joke. You have multiple resources being spent to investigate these cases," said Santa Cruz County Sheriff's Sgt. Roy Morales. The schools remained open throughout the week, with a huge police presence on campus. In an anonymous emailed statement to the Daily Pilot on Thursday, the "Ogle team" said: "We are aware of the concern, and cyberbullying is absolutely NOT our intention for the app. Our goal for this app is to create a free and safe community space for students, for a better communication. We are currently working around the clock to improve the app. As a matter of fact, we are also in contact with local police departments, anti-bullying organizations and local high schools to try to help the students." In response to these incidents, Ogle expressed that they takes the safety of its users seriously and does not condone any type of behavior that is illegal or in violation of its content policies. The company also said it has instituted a content moderation team to increase review and identify and remove inappropriate content, and take action against “those who violate our community guidelines.”

  Read more →
• 

  Sports Card Investor

  Sports Card Investor is an American sports collectibles media platform and mobile application founded by Geoff Wilson. The platform provides market data, analysis, and editorial content focused on sports trading cards and related collectibles. It operates a website, mobile app, and digital media channels covering developments in the sports card industry. The company posted its first YouTube video in July 2019, shortly before a period of rapid growth in sports card collecting in the early 2020s, which was marked by increased trading volumes and mainstream media attention. == History == Sports Card Investor was founded by Geoff Wilson, an entrepreneur and collector who began publishing sports card–related content online before launching the platform's dedicated app and subscription tools. In February 2020, the company launched Market Movers, the first website and app to chart sports card prices and track card collections. The platform expanded its media presence through partnerships and distribution agreements. In 2023, Yahoo Sports announced a new collectibles coverage initiative that included additional content from Sports Card Investor. In February 2024, the Sports Card Investor studio relocated to CardsHQ in Atlanta, Georgia, and visitors to the facility can watch Sports Card Investor videos being filmed. == Platform and content == The Sports Card Investor app provides users with pricing data, portfolio-tracking tools, and market-trend analysis for trading cards. The company also produces video and editorial content discussing market developments, grading trends, and major card releases. Coverage in industry publications has referenced Sports Card Investor in discussions about shifts in sports card licensing rights and hobby market reactions. == Industry context == The growth of Sports Card Investor coincided with a broader resurgence in trading card markets, including record sales and expanded retail presence. Mainstream outlets have cited the company and its founder in reporting on collectibles investing trends, grading practices, and market volatility. The Sports Card Investor app has attracted over 37,000 reviews on the Apple App Store, reflecting its strong user engagement within the sports card community.

  Read more →
• 

  Vision transformer

  A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into tokens), serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings. ViTs were designed as alternatives to convolutional neural networks (CNNs) in computer vision applications. They have different inductive biases, training stability, and data efficiency. Compared to CNNs, ViTs are less data efficient, but have higher capacity. Some of the largest modern computer vision models are ViTs, such as one with 22B parameters. Subsequent to its publication, many variants were proposed, with hybrid architectures with both features of ViTs and CNNs. ViTs have found application in image recognition, image segmentation, weather prediction, and autonomous driving. == History == Transformers were introduced in Attention Is All You Need (2017), and have found widespread use in natural language processing. A 2019 paper applied ideas from the Transformer to computer vision. Specifically, they started with a ResNet, a standard convolutional neural network used for computer vision, and replaced all convolutional kernels by the self-attention mechanism found in a Transformer. It resulted in superior performance. However, it is not a Vision Transformer. In 2020, an encoder-only Transformer was adapted for computer vision, yielding the ViT, which reached state of the art in image classification, overcoming the previous dominance of CNN. The masked autoencoder (2022) extended ViT to work with unsupervised training. The vision transformer and the masked autoencoder, in turn, stimulated new developments in convolutional neural networks. Subsequently, there was cross-fertilization between the previous CNN approach and the ViT approach. In 2021, some important variants of the Vision Transformers were proposed. These variants are mainly intended to be more efficient, more accurate or better suited to a specific domain. Two studies improved efficiency and robustness of ViT by adding a CNN as a preprocessor. The Swin Transformer achieved state-of-the-art results on some object detection datasets such as COCO, by using convolution-like sliding windows of attention mechanism, and the pyramid process in classical computer vision. == Overview == The basic architecture, used by the original 2020 paper, is as follows. In summary, it is a BERT-like encoder-only Transformer. The input image is of type R H × W × C {\displaystyle \mathbb {R} ^{H\times W\times C}} , where H , W , C {\displaystyle H,W,C} are height, width, channel (RGB). It is then split into square-shaped patches of type R P × P × C {\displaystyle \mathbb {R} ^{P\times P\times C}} . For each patch, the patch is pushed through a linear operator, to obtain a vector ("patch embedding"). The position of the patch is also transformed into a vector by "position encoding" (the paper tried no embedding, 1D embedding, 2D embedding, and relative embedding: 1D was adopted). The two vectors are added, then pushed through several Transformer encoders. The attention mechanism in a ViT repeatedly transforms representation vectors of image patches, incorporating more and more semantic relations between image patches in an image. This is analogous to how in natural language processing, as representation vectors flow through a transformer, they incorporate more and more semantic relations between words, from syntax to semantics. The above architecture turns an image into a sequence of vector representations. To use these for downstream applications, an additional head needs to be trained to interpret them. For example, to use it for classification, one can add a shallow MLP on top of it that outputs a probability distribution over classes. The original paper uses a linear-GeLU-linear-softmax network. == Variants == === Original ViT === The original ViT was an encoder-only Transformer supervise-trained to predict the image label from the patches of the image. As in the case of BERT, it uses a special token in the input side, and the corresponding output vector is used as the only input of the final output MLP head. The special token is an architectural hack to allow the model to compress all information relevant for predicting the image label into one vector. Transformers found their initial applications in natural language processing tasks, as demonstrated by language models such as BERT and GPT-3. By contrast the typical image processing system uses a convolutional neural network (CNN). Well-known projects include Xception, ResNet, EfficientNet, DenseNet, and Inception. Transformers measure the relationships between pairs of input tokens (words in the case of text strings), termed attention. The cost is quadratic in the number of tokens. For images, the basic unit of analysis is the pixel. However, computing relationships for every pixel pair in a typical image is prohibitive in terms of memory and computation. Instead, ViT computes relationships among pixels in various small sections of the image (e.g., 16x16 pixels), at a drastically reduced cost. The sections (with positional embeddings) are placed in a sequence. The embeddings are learnable vectors. Each section is arranged into a linear sequence and multiplied by the embedding matrix. The result, with the position embedding is fed to the transformer. === Architectural improvements === ==== Pooling ==== After the ViT processes an image, it produces some embedding vectors. These must be converted to a single class probability prediction by some kind of network. In the original ViT and Masked Autoencoder, they used a dummy [CLS] token, in emulation of the BERT language model. The output at [CLS] is the classification token, which is then processed by a LayerNorm-feedforward-softmax module into a probability distribution. Global average pooling (GAP) does not use the dummy token, but simply takes the average of all output tokens as the classification token. It was mentioned in the original ViT as being equally good. Multihead attention pooling (MAP) applies a multiheaded attention block to pooling. Specifically, it takes as input a list of vectors x 1 , x 2 , … , x n {\displaystyle x_{1},x_{2},\dots ,x_{n}} , which might be thought of as the output vectors of a layer of a ViT. The output from MAP is M u l t i h e a d e d A t t e n t i o n ( Q , V , V ) {\displaystyle \mathrm {MultiheadedAttention} (Q,V,V)} , where q {\displaystyle q} is a trainable query vector, and V {\displaystyle V} is the matrix with rows being x 1 , x 2 , … , x n {\displaystyle x_{1},x_{2},\dots ,x_{n}} . This was first proposed in the Set Transformer architecture. Later papers demonstrated that GAP and MAP both perform better than BERT-like pooling. A variant of MAP was proposed as class attention, which applies MAP, then feedforward, then MAP again. Re-attention was proposed to allow training deep ViT. It changes the multiheaded attention module. === Masked Autoencoder === The Masked Autoencoder took inspiration from denoising autoencoders and context encoders. It has two ViTs put end-to-end. The first one ("encoder") takes in image patches with positional encoding, and outputs vectors representing each patch. The second one (called "decoder", even though it is still an encoder-only Transformer) takes in vectors with positional encoding and outputs image patches again. ==== Training ==== During training, input images (224px x 224 px in the original implementation) are split along a designated number of lines on each axis, producing image patches. A certain percentage of patches are selected to be masked out by mask tokens, while all others are retained in the image. The network is tasked with reconstructing the image from the remaining unmasked patches. Mask tokens in the original implementation are learnable vector quantities. A linear projection with positional embeddings is then applied to the vector of unmasked patches. Experiments varying mask ratio on networks trained on the ImageNet-1K dataset found 75% mask ratios achieved high performance on both finetuning and linear-probing of the encoder's latent space. The MAE processes only unmasked patches during training, increasing the efficiency of data processing in the encoder and lowering the memory usage of the transformer. A less computationally-intensive ViT is used for the decoder in the original implementation of the MAE. Masked patches are added back to the output of the encoder block as mask tokens and both are fed into the decoder. A reconstruction loss is computed for the masked patches to assess network performance. ==== Prediction ==== In prediction, the decoder architecture is discarded entirely. The input image is split into patches by the same algorithm as in training, but no patches are masked out. A linear projection wi

  Read more →
• 

  ViBe

  ViBe is a background subtraction algorithm which has been presented at the IEEE ICASSP 2009 conference and was refined in later publications. More precisely, it is a software module for extracting background information from moving images. It has been developed by Oliver Barnich and Marc Van Droogenbroeck of the Montefiore Institute, University of Liège, Belgium. ViBe is patented: the patent covers various aspects such as stochastic replacement, spatial diffusion, and non-chronological handling. ViBe is written in the programming language C, and has been implemented on CPU, GPU and FPGA. == Technical description == Source: === Pixel model and classification process === Many advanced techniques are used to provide an estimate of the temporal probability density function (pdf) of a pixel x. ViBe's approach is different, as it imposes the influence of a value in the polychromatic space to be limited to the local neighborhood. In practice, ViBe does not estimate the pdf, but uses a set of previously observed sample values as a pixel model. To classify a value pt(x), it is compared to its closest values among the set of samples. === Model update: Sample values lifespan policy === ViBe ensures a smooth exponentially decaying lifespan for the sample values that constitute the pixel models. This makes ViBe able to successfully deal with concomitant events with a single model of a reasonable size for each pixel. This is achieved by choosing, randomly, which sample to replace when updating a pixel model. Once the sample to be discarded has been chosen, the new value replaces the discarded sample. The pixel model that would result from the update of a given pixel model with a given pixel sample cannot be predicted since the value to be discarded is chosen at random. === Model update: Spatial Consistency === To ensure the spatial consistency of the whole image model and handle practical situations such as small camera movements or slowly evolving background objects, ViBe uses a technique similar to that developed for the updating process in which it chooses at random and update a pixel model in the neighborhood of the current pixel. By denoting NG(x) and p(x) respectively the spatial neighborhood of a pixel x and its value, and assuming that it was decided to update the set of samples of x by inserting p(x), then ViBe also use this value p(x) to update the set of samples of one of the pixels in the neighborhood NG(x), chosen at random. As a result, ViBe is able to produce spatially coherent results directly without the use of any post-processing method. === Model initialization === Although the model could easily recover from any type of initialization, for example by choosing a set of random values, it is convenient to get an accurate background estimate as soon as possible. Ideally a segmentation algorithm would like to be able to segment the video sequences starting from the second frame, the first frame being used to initialize the model. Since no temporal information is available prior to the second frame, ViBe populates the pixel models with values found in the spatial neighborhood of each pixel; more precisely, it initializes the background model with values taken randomly in each pixel neighborhood of the first frame. The background estimate is therefore valid starting from the second frame of a video sequence.

  Read more →