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
Nona-binning
Nona-binning is a pixel binning technique used in high-resolution image sensors, primarily in smartphone cameras. The method is based on merging groups of nine neighbouring pixels arranged in a 3×3 pattern. This configuration allows a sensor with very small individual pixels to increase its effective light sensitivity when operating in low-light conditions, while still maintaining high nominal resolution in bright environments. == Overview == Nona-binning is most commonly implemented in sensors with a resolution of 108 megapixels and higher. As pixel counts grew, the physical dimensions of individual pixels continued to shrink, reducing the amount of light captured by each. The 3×3 binning structure enables a sensor to operate in two modes. In well-lit scenes, each pixel is processed separately, providing the full resolution of the sensor. In darker settings, nine pixels with identical colour filters are combined into a single output unit, increasing signal strength and reducing noise. == Technical principles == Unlike the traditional Bayer colour filter array, which alternates colours on a per-pixel basis, nona-binning uses a grouped layout. The sensor forms blocks of nine pixels with matching colour filters — typically within a Quad Bayer–derived arrangement extended to 3×3 regions. When operating in the binning mode, the sensor aggregates the charge generated by all nine pixels in each block. This increases effective sensitivity but lowers the final image resolution. When lighting conditions allow, the sensor returns to processing pixel data individually. == Applications == Nona-binning is primarily used in: Smartphone photography, particularly in devices equipped with sensors exceeding 100 megapixels. Low-light imaging, where increased sensitivity improves exposure stability and reduces noise. Computational photography systems, such as multi-frame processing and HDR capture. == Related technologies == Nona-binning belongs to the broader group of pixel-binning approaches used in modern sensors. Other implementations include Tetracell, which merges four pixels in a 2×2 block, and hexa-binning, which combines six pixels, though it is less common. All of these methods aim to balance the high nominal resolution of mobile sensors with the need for improved low-light performance.
Artificial intelligence industry in Taiwan
The artificial intelligence (AI) industry in Taiwan refers to the development, application, and commercialization of artificial intelligence technologies within Taiwan. The industry has grown alongside Taiwan's established strengths in semiconductor manufacturing and information and communications technology (ICT), and is supported by government policy, research institutions, and private sector participation. AI development in Taiwan has focused on integrating hardware capabilities with software applications across sectors such as manufacturing, healthcare, and smart infrastructure. Artificial intelligence has been identified as a strategic area of development in Taiwan since the late 2010s. While Taiwan has historically played a limited role in early theoretical and expert-system phases of AI development, its position in global electronics manufacturing has provided a foundation for participation in the contemporary era of machine learning and data-driven AI systems. Taiwan's AI industry is characterized by a strong hardware base, particularly in semiconductor production and AI server manufacturing, combined with increasing investment in software, data infrastructure, and applied AI services. The sector has been shaped by global demand for computing power, advances in deep learning, and the expansion of AI applications in industrial and commercial contexts. == Government policy and development == The Taiwanese government has promoted AI development through a series of national strategies. In 2017, the Ministry of Science and Technology launched the "AI Grand Strategy for a Small Country" initiative, investing approximately US$517 million between 2017 and 2021 to support research, infrastructure, and talent development. This initiative aimed to build a domestic AI ecosystem by funding research centers, expanding data infrastructure, and supporting industrial adoption. The Executive Yuan also introduced the AI Taiwan Action Plan 1.0 (2018–2021), which focused on integrating AI technologies into existing industries and strengthening research and development capabilities. A subsequent plan, AI Taiwan Action Plan 2.0 (2023–2026), expanded the focus to include ethical governance, regulatory frameworks, and risk management in response to the growth of generative AI technologies. In 2023, the Taiwan AI Center of Excellence (Taiwan AICoE), a government-backed hub, was established by the National Science and Technology Council to accelerate AI development, foster international collaboration, and train talent in Taiwan. It acts as a specialized think tank focusing on creating a "smart technology island" by integrating AI resources and developing trusted, human-centric AI technologies. In 2024, the Taiwan Chip-based Industrial Innovation Program (CbI) was launched by the Executive Yuan as a 10-year, NT$300 billion (US$9.3 billion) initiative to leverage Taiwan's semiconductor dominance, driving innovation in AI, smart mobility, manufacturing, and healthcare. It aims to combine generative AI with IC technology, cultivate talent, and attract global startups to build a "Silicon Island". In parallel, the Taiwanese government has explored legislative frameworks such as a proposed Artificial Intelligence Fundamental Act in December 2025, addressing issues including data protection, safety standards, and intellectual property. == Industrial structure == === Semiconductor and hardware foundation === Taiwan's AI industry is closely linked to its semiconductor sector. In 2020, Taiwan accounted for approximately 77.3% of the global wafer foundry market and 57.7% of packaging and testing, with a 20.1% share in integrated circuit (IC) design. These capabilities provide critical infrastructure for AI systems, which rely on high-performance computing hardware. Taiwanese firms are also involved in the production of AI servers and related components, contributing significantly to global supply chains for data centers and cloud computing. The integration of chip design, manufacturing, and assembly has enabled Taiwan to play a central role in providing the computational resources required for AI development. On 20 November 2025, Google established the "Google Taiwan AI Infrastructure R&D Center", second only to its US headquarters and largest AI hardware infrastructure engineering center outside of the United States. === Software and services === Compared to its hardware capabilities, Taiwan's AI software sector is less developed. The absence of large-scale global AI platform companies has been noted as a structural limitation. As a result, much of Taiwan's AI industry focuses on applied solutions, including customization of existing AI models for specific industries. Therefore, efforts to strengthen software capabilities have included investment in research institutions, startup ecosystems, and collaborations between academia and industry. == Applications == === Smart manufacturing === AI has been widely applied in Taiwan's manufacturing sector, which is a major component of the economy. Applications include process automation, predictive maintenance, quality control, and fault detection. AI-enabled smart manufacturing systems aim to improve efficiency, reduce production costs, and enhance product quality. Taiwan's manufacturing industry has incorporated AI technologies into production lines, particularly in electronics and machinery sectors. === Healthcare === The use of AI in healthcare in Taiwan has expanded in areas such as medical imaging, diagnostics, and drug development. AI systems are used to analyze CT scans, MRI data, and other clinical information to support diagnosis and treatment planning. Taiwan's healthcare sector, which includes medical devices, pharmaceuticals, and medical services, has benefited from the integration of AI technologies, particularly in precision medicine and clinical decision support systems. A notable example of AI healthcare deployment in Taiwan is the collaboration between Siemens Healthineers, Ever Fortune AI, and Asia University Hospital. === Edge computing and IoT === AI applications in Taiwan increasingly involve edge computing, where data processing occurs near the source rather than in centralized cloud systems. This approach reduces latency and bandwidth requirements and is used in smart devices, sensors, and industrial equipment. Edge AI technologies are applied in areas such as smart appliances, industrial automation, and transportation systems. == Education and talent development == Human capital development has been a key focus of Taiwan's AI strategy. The Taiwan AI Academy, established in 2018 with support from Academia Sinica and industry partners, provides training programs for professionals and students aimed at accelerating the adoption of artificial intelligence technologies across industries. The academy offers a range of courses, including executive-level programs, technical training, and specialized tracks in areas such as smart manufacturing, smart healthcare, and edge AI. These programs are designed to provide intensive and practical instruction over relatively short periods. A notable component of the curriculum is project-based learning, in which participants are required to complete proof-of-concept (POC) projects addressing real-world industrial problems. These projects are often developed further for implementation within companies, facilitating technology transfer and commercialization. Between 2018 and 2021, more than 8,000 individuals completed AI training programs across campuses in Taipei, Hsinchu, Taichung, and Tainan. Graduates of the academy have contributed to the introduction of AI systems in sectors such as manufacturing, healthcare, and finance, supporting broader industrial transformation efforts. In addition to the Taiwan AI Academy, universities and research institutions in Taiwan play a significant role in AI education and research. Leading universities have expanded programs in computer science, data science, and machine learning, while research institutes conduct applied and fundamental studies in artificial intelligence. Collaboration between academia, government, and industry is a common feature of Taiwan's AI ecosystem, with joint research projects, internship programs, and technology incubation initiatives supporting talent development. Government-supported initiatives have also sought to attract and retain AI talent, including funding for graduate education, international collaboration programs, and incentives for industry–academic partnerships. These efforts aim to address talent shortages and strengthen Taiwan's capacity in both applied and foundational AI research. == Regulation and governance == Taiwan has developed guidelines and policy frameworks to address the risks associated with AI technologies. In 2023, the Executive Yuan issued guidelines for the use of generative AI in government agencies, focusing on data security and privacy. Ongoing policy discussions hav
EdgeRank
EdgeRank is the name commonly given to the algorithm that Facebook uses to determine what articles should be displayed in a user's News Feed. As of 2011, Facebook has stopped using the EdgeRank system and uses a machine learning algorithm that, as of 2013, takes more than 100,000 factors into account. EdgeRank was developed and implemented by Serkan Piantino. == Formula and factors == In 2010, a simplified version of the EdgeRank algorithm was presented as: ∑ e d g e s e u e w e d e {\displaystyle \sum _{\mathrm {edges\,} e}u_{e}w_{e}d_{e}} where: u e {\displaystyle u_{e}} is user affinity. w e {\displaystyle w_{e}} is how the content is weighted. d e {\displaystyle d_{e}} is a time-based decay parameter. User Affinity: The User Affinity part of the algorithm in Facebook's EdgeRank looks at the relationship and proximity of the user and the content (post/status update). Content Weight: What action was taken by the user on the content. Time-Based Decay Parameter: New or old. Newer posts tend to hold a higher place than older posts. Some of the methods that Facebook uses to adjust the parameters are proprietary and not available to the public. A study has shown that it is possible to hypothesize a disadvantage of the "like" reaction and advantages of other interactions (e.g., the "haha" reaction or "comments") in content algorithmic ranking on Facebook. The "like" button can decrease the organic reach as a "brake effect of viral reach". The "haha" reaction, "comments" and the "love" reaction could achieve the highest increase in total organic reach. == Impact == EdgeRank and its successors have a broad impact on what users actually see out of what they ostensibly follow: for instance, the selection can produce a filter bubble (if users are exposed to updates which confirm their opinions etc.) or alter people's mood (if users are shown a disproportionate amount of positive or negative updates). As a result, for Facebook pages, the typical engagement rate is less than 1% (or less than 0.1% for the bigger ones), and organic reach 10% or less for most non-profits. As a consequence, for pages, it may be nearly impossible to reach any significant audience without paying to promote their content.
MaPS S.A.
MaPS S.A. is a software editor founded in 2011 by Thierry Muller. The company is headquartered in Luxembourg. Its platform, called MaPS System, provides Data Management software for Multichannel Marketing. == History and funding == The first version of MaPS System was released under the agency Prem1um S.A. in 2005 in the partnership with Pingroom agency. In combination with MaPS System, Prem1um also provided various consulting services in Marketing, Publishing and Sales. This is where MaPS System takes its names (M stands for Marketing, P for Publishing and S for Sales). In 2011, after being successful, Prem1um S.A. decided to enable the software MaPS System to operate independently under MaPS S.A., as a separate company and editor of the software. The first financial supports were provided by Malta ICI, a Venture Capital firm, and the local partner Chameleon Invest, a seed-capital fund led by Business Angels, who invested €900,000. In a second investment round in 2014 led by Newion Investments, a Venture Capital firm, €1.4 Million were raised, thus amounting to total assets of €2.2 Million. In 2016, the company was taken over by three private investors. In 2018, after two years of continuous growth and European expansion in Belgium, Germany and Switzerland, MaPS S.A acquired Awevo, an e-commerce web agency. == Products == The services included in MaPS System range from the data centralization, Data Governance to an optimized Multichannel Marketing. The software currently includes more than 35 modules for Master Data Management, Product Information Management, Digital Asset Management, Business Process Management including catalogue Publishing features. == Certifications == In 2019, MaPS System and Awevo received "Made in Luxembourg" label, given to the companies whose services are entirely designed in Luxembourg, without any production or development offshoring. MaPS System is a member of ICT Cluster by Luxinnovation.
National Parking Platform
The National Parking Platform is a digital platform in the United Kingdom providing interoperability between car park operators, parking apps, and other service providers. It enables all parking apps that support the system: RingGo, JustPark, PayByPhone, Apcoa Connect, AppyParking, and Caura to work at all participating car parks. It has been rolled out in 13 local authorities so far. It was first developed by the Department for Transport starting in 2019, and since May 2025 is controlled by the British Parking Association on a not-for-profit basis. == Participating local authorities == Buckinghamshire Cheshire West and Chester Coventry City East Hertfordshire East Suffolk Liverpool City Manchester City Oxfordshire County Peterborough City Stevenage Sutton Walsall Welwyn Hatfield
Birkhoff algorithm
Birkhoff's algorithm (also called Birkhoff-von-Neumann algorithm) is an algorithm for decomposing a bistochastic matrix into a convex combination of permutation matrices. It was published by Garrett Birkhoff in 1946. It has many applications. One such application is for the problem of fair random assignment: given a randomized allocation of items, Birkhoff's algorithm can decompose it into a lottery on deterministic allocations. == Terminology == A bistochastic matrix (also called: doubly-stochastic) is a matrix in which all elements are greater than or equal to 0 and the sum of the elements in each row and column equals 1. An example is the following 3-by-3 matrix: ( 0.2 0.3 0.5 0.6 0.2 0.2 0.2 0.5 0.3 ) {\displaystyle {\begin{pmatrix}0.2&0.3&0.5\\0.6&0.2&0.2\\0.2&0.5&0.3\end{pmatrix}}} A permutation matrix is a special case of a bistochastic matrix, in which each element is either 0 or 1 (so there is exactly one "1" in each row and each column). An example is the following 3-by-3 matrix: ( 0 1 0 0 0 1 1 0 0 ) {\displaystyle {\begin{pmatrix}0&1&0\\0&0&1\\1&0&0\end{pmatrix}}} A Birkhoff decomposition (also called: Birkhoff-von-Neumann decomposition) of a bistochastic matrix is a presentation of it as a sum of permutation matrices with non-negative weights. For example, the above matrix can be presented as the following sum: 0.2 ( 0 1 0 0 0 1 1 0 0 ) + 0.2 ( 1 0 0 0 1 0 0 0 1 ) + 0.1 ( 0 1 0 1 0 0 0 0 1 ) + 0.5 ( 0 0 1 1 0 0 0 1 0 ) {\displaystyle 0.2{\begin{pmatrix}0&1&0\\0&0&1\\1&0&0\end{pmatrix}}+0.2{\begin{pmatrix}1&0&0\\0&1&0\\0&0&1\end{pmatrix}}+0.1{\begin{pmatrix}0&1&0\\1&0&0\\0&0&1\end{pmatrix}}+0.5{\begin{pmatrix}0&0&1\\1&0&0\\0&1&0\end{pmatrix}}} Birkhoff's algorithm receives as input a bistochastic matrix and returns as output a Birkhoff decomposition. == Tools == A permutation set of an n-by-n matrix X is a set of n entries of X containing exactly one entry from each row and from each column. A theorem by Dénes Kőnig says that: Every bistochastic matrix has a permutation-set in which all entries are positive.The positivity graph of an n-by-n matrix X is a bipartite graph with 2n vertices, in which the vertices on one side are n rows and the vertices on the other side are the n columns, and there is an edge between a row and a column if the entry at that row and column is positive. A permutation set with positive entries is equivalent to a perfect matching in the positivity graph. A perfect matching in a bipartite graph can be found in polynomial time, e.g. using any algorithm for maximum cardinality matching. Kőnig's theorem is equivalent to the following:The positivity graph of any bistochastic matrix admits a perfect matching.A matrix is called scaled-bistochastic if all elements are non-negative, and the sum of each row and column equals c, where c is some positive constant. In other words, it is c times a bistochastic matrix. Since the positivity graph is not affected by scaling:The positivity graph of any scaled-bistochastic matrix admits a perfect matching. == Algorithm == Birkhoff's algorithm is a greedy algorithm: it greedily finds perfect matchings and removes them from the fractional matching. It works as follows. Let i = 1. Construct the positivity graph GX of X. Find a perfect matching in GX, corresponding to a positive permutation set in X. Let z[i] > 0 be the smallest entry in the permutation set. Let P[i] be a permutation matrix with 1 in the positive permutation set. Let X := X − z[i] P[i]. If X contains nonzero elements, Let i = i + 1 and go back to step 2. Otherwise, return the sum: z[1] P[1] + ... + z[2] P[2] + ... + z[i] P[i]. The algorithm is correct because, after step 6, the sum in each row and each column drops by z[i]. Therefore, the matrix X remains scaled-bistochastic. Therefore, in step 3, a perfect matching always exists. == Run-time complexity == By the selection of z[i] in step 4, in each iteration at least one element of X becomes 0. Therefore, the algorithm must end after at most n2 steps. However, the last step must simultaneously make n elements 0, so the algorithm ends after at most n2 − n + 1 steps, which implies O ( n 2 ) {\displaystyle O(n^{2})} . In 1960, Joshnson, Dulmage and Mendelsohn showed that Birkhoff's algorithm actually ends after at most n2 − 2n + 2 steps, which is tight in general (that is, in some cases n2 − 2n + 2 permutation matrices may be required). == Application in fair division == In the fair random assignment problem, there are n objects and n people with different preferences over the objects. It is required to give an object to each person. To attain fairness, the allocation is randomized: for each (person, object) pair, a probability is calculated, such that the sum of probabilities for each person and for each object is 1. The probabilistic-serial procedure can compute the probabilities such that each agent, looking at the matrix of probabilities, prefers his row of probabilities over the rows of all other people (this property is called envy-freeness). This raises the question of how to implement this randomized allocation in practice? One cannot just randomize for each object separately, since this may result in allocations in which some people get many objects while other people get no objects. Here, Birkhoff's algorithm is useful. The matrix of probabilities, calculated by the probabilistic-serial algorithm, is bistochastic. Birkhoff's algorithm can decompose it into a convex combination of permutation matrices. Each permutation matrix represents a deterministic assignment, in which every agent receives exactly one object. The coefficient of each such matrix is interpreted as a probability; based on the calculated probabilities, it is possible to pick one assignment at random and implement it. == Extensions == The problem of computing the Birkhoff decomposition with the minimum number of terms has been shown to be NP-hard, but some heuristics for computing it are known. This theorem can be extended for the general stochastic matrix with deterministic transition matrices. Budish, Che, Kojima and Milgrom generalize Birkhoff's algorithm to non-square matrices, with some constraints on the feasible assignments. They also present a decomposition algorithm that minimizes the variance in the expected values. Vazirani generalizes Birkhoff's algorithm to non-bipartite graphs. Valls et al. showed that it is possible to obtain an ϵ {\displaystyle \epsilon } -approximate decomposition with O ( log ( 1 / ϵ 2 ) ) {\displaystyle O(\log(1/\epsilon ^{2}))} permutations.