AI App Kisne Banaya

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

  • Engineering Historical Memory

    Engineering Historical Memory

    Engineering Historical Memory (EHM) is an online database in the digital humanities, serving as an open-access research tool for primary historical materials focused on 11th to 15th century Afro-Eurasia. It adopts computational methods to make historical documents machine-understandable. EHM parses traditional artifacts such as historical maps, travel accounts, chronicles and codices into computer-readable formats, and links them to secondary multi-media references, a process referred to as the "automatic narrative generation". This approach generates cultural narratives and facilitates interaction with the historical artifacts, making them accessible to audiences from various backgrounds. == History == EHM was first theorised in 2007 by researcher Andrea Nanetti when he was a visiting scholar at Princeton University, and the preliminary test results were published between 2008 and 2011. In 2013, the EHM research team was set up in Singapore following Nanetti's professorship at Nanyang Technological University (NTU). Two years later, after receiving several Microsoft research grants, EHM went live on Microsoft Azure. In 2018, the College of Humanities, Arts and Social Sciences (CoHASS) at NTU Singapore formed the Digital Humanities Research Cluster, as part of which, EHM has been an ongoing interdisciplinary research project led by Nanetti. Partnering with international educational and cultural institutions such as Ca' Foscari University of Venice, University of Florence, Taylor & Francis Group, Delft University of Technology (TUDelft), and SenticNet, EHM has been supported by over 130 scholars and engineers. == Applications == Primary historical materials on EHM are curated into several categories, including maps, travel accounts, chronicles, codices, sites, archival documents, and paintings, such as the Morosini Codex (listed under Chronicles) and Pope Gregory X's Privilege for the Holy Monastery of St Catherine of Sinai (listed under Archival Documents). EHM has been adopted by cultural organisations as an exhibition and research tool in the digital humanities field. An example is the publication of a digital interactive edition of Fra Mauro's Map of the World on EHM, a collaboration project between NTU Singapore and the Biblioteca Nazionale Marciana of Venice. The digitisation process of the map on EHM involved transcribing and geo-referencing the textual content in the 15th-century map, followed by creating semantic annotations to connect the map's content with related secondary data sources. The e-map was subsequently adopted and launched online by Museo Galileo in March 2022 and incorporated into the virtual exhibition "Venezia and Suzhou: Water Cities along the Silk Roads" (online, September-December 2022). In 2024, the Fra Mauro's Map of the World application on EHM was awarded the Digital Humanities and Multimedia Studies Prize (DHMS) by the Medieval Academy of America. Image-Based Video Search Engine is another experimental project under the EHM scope led by the research teams at Delft University of Technology (TUDelft) and NTU Singapore. This ongoing project aims to improve the efficiency of retrieving targeted objects from audio-visuals. == Awards == In 2021, EHM won the GLAMi Awards (MuseWeb Conference - Galleries, Libraries, Archives, and Museums Innovation awards) in the "Resources for Scholars and Researchers" category. In the same year, EHM was a Falling Walls finalist for Science Breakthrough of the Year in the category Social Sciences and Humanities after nominated by the School of Advanced Study at the University of London. In April 2022, the Italian National Commission for UNESCO has selected and sent the EHM project to the organisers of the "Jikji Memory of the World" Award for final evaluation. In January 2024, the Medieval Academy of America announced its 2024 Digital Humanities and Multimedia Studies Prize (DHMS) goes to the Fra Mauro's Map of the World application on EHM.

    Read more →
  • Ancient text corpora

    Ancient text corpora

    Ancient text corpora are the entire collection of texts from the period of ancient history, defined in this article as the period from the beginning of writing up to 300 AD. These corpora are important for the study of literature, history, linguistics, and other fields, and are a fundamental component of the world's cultural heritage. Chinese, Latin, and Greek are examples of ancient languages with significant text corpora, although much of these corpora are known to us via transmission (frequently via medieval manuscript copies) rather than in their original form. These texts – both transmitted and original – provide valuable insights into the history and culture of different regions of the world, and have been studied for centuries by scholars and researchers. Other ancient texts – particularly stone inscriptions and papyrus scrolls – have been published following archaeological research, notably the cuneiform corpus of c.10 million words and the c.5 million words in ancient Egyptian. Through advances in technology and digitization, ancient text corpora are more accessible than ever before. Tools such as the Perseus Digital Library and the Digital Corpus of Sanskrit have made it easier for researchers to access and analyze these texts. == Quantifying the corpora == Two types of ancient texts are known to modern scholars – those that have only survived in younger manuscripts, but whose great age is undisputed (this applies to the bulk of the Chinese, Brahmi, Greek, Latin, Hebrew and Avestan tradition), and those known from original inscriptions, papyri and other manuscripts. Counting of the words in each corpus presents significant methodological challenges – in principle, every single occurrence of a word in the text is counted separately, but in the case of parallel transmission of literary texts, only a single transmission is taken into account. Just as the Book of the Dead and the coffin texts are only included once in the number given for the Egyptian, the Greek and Latin literary works should only be counted according to one manuscript. If, on the other hand, tombs, royal inscriptions or economic documents of certain ancient languages often show a more or less identical form, this is not evaluated as a purely "parallel tradition". Attached prepositions are counted as separate words, except in the case of the definite article in Hebrew, Aramaic and Greek since it has no equivalent in most languages, so its frequency would significantly affect the comparability of numbers. === Languages with known size estimates === === South Asian === Sanskrit (Vedic Sanskrit and Classical Sanskrit) Indus script (3,800 items, c.20,000 characters) Brahmi script Old Tamil Early Indian epigraphy and Indian epic poetry Kharosthi Pali literature List of historic Indian texts === Mesoamerican === Olmec hieroglyphs Maya script === East Asian === Old Chinese Chinese classics The pre-Qin corpus: a collection of ancient Chinese texts written before the Qin dynasty (221 BCE). The corpus includes texts from Confucianism, Taoism, Legalism, and other schools of thought. The pre-Han corpus: a collection of ancient Chinese texts written before the Han dynasty (202 BCE). The corpus includes texts from Confucianism, Taoism, Legalism, and other schools of thought. See the Chinese Text Project Chinese bronze inscriptions, Oracle bone script, Seal script, Clerical script === Central Iranian languages === Prior to 300 AD, the Central Iranian languages are mainly in the form of Sassanid stone inscriptions in the two closely related idioms Middle Persian (Pahlavi scripts and Inscriptional Parthian), there are 5000 for the corpus of Middle Persian (mostly 3rd, but also 4th/5th centuries) and for the corpus of Parthian (3rd century) 3000 words. To what extent some of the Manichaean Middle Persian literary texts may date back to the 3rd century is difficult to estimate; Mani is said to have personally written the Shabuhragan totaling about 5000 words. In any case, if we combine Middle Persian and Parthian, we come to over 10,000 words. === Proto-Sinaitic === Proto-Sinaitic script has no more than about 400 letters (number of words is unknown since the script has not been fully interpreted). To a similar extent, there are probably approximately contemporaneous Proto-Canaanite inscriptions (ibid.). === Anatolian === Luwian cuneiform, approx. 3000 words the Palaic language few hundred words. Hieroglyphic Luwian the Lycian alphabet (the best attested Anatolian successor language written in alphabetic script) with about 5000 words The Lydian alphabet 109 inscriptions comprising about 1500 words The Phrygian alphabet the in-tomb inscriptions from the 2nd and 3rd centuries AD (approx. 1000 words) and in the so-called "old Phrygian" inscriptions less than 300 words The Carian alphabets whose texts, mainly from Egypt, contain around 600 words. === Old Italic === the Umbrian language attested essentially by the sacrificial instructions of the Iguvinian Tables with 5000 words the Oscan language (ibid.) with 2000 words the Messapic language with probably a good 1000 words (the estimate is difficult because most texts in this hardly understandable language do not use word separators) the Venetic language a few hundred words the Faliscan language a few hundred words Cisalpine Celtic inscriptions amount to approximately 2000 words, to which are added a number of glosses by classical authors === Iberia === Iberian scripts, more rarely written in Greek or Latin script, approx. 2500 words Celtiberian script, which refers to Celtic language testimonies in Iberian, but also in Latin script from Spain (approx. 1000 words) Southwest Paleohispanic script, 78 inscriptions, a few hundred words Lusitanian language, three monuments in Latin script, approx. 60 words === Germanic Northern Europe === Runic inscriptions dated before the 4th century amount to about 30 pieces, which contain no more than 50 words in total === Africa === Geʽez script: comparatively few inscriptions with a total of around 1,000 words before 300 AD. Following Christianization in the 4th century, more extensive texts are known. Libyco-Berber alphabet: over 1,000 inscriptions from the Maghreb, which are dated to Roman times. Most texts do not use a word separator; Peust estimates that the total number of words could be around 5,000 Meroitic script (Ancient Nubian): about 900 texts are known, which Peust estimates may contain approximately 10,000 words, albeit with uncertainty from the fact that the word separator is not used consistently in the Meroitic script. === Aegean === The Cretan Linear A inscriptions that have not yet been deciphered are available in about 2500 texts, which contain a total of around 20,000 characters. The total number of words can hardly be determined; Peust tentatively put it in the same order of magnitude as in Meroitic. In addition to the Linear A texts, there are also inscriptions Cretan hieroglyphs of a few hundred characters and texts written in the Greek alphabet, but not in Greek, with a few dozen words Cypriot syllabary in the first millennium BC, in which mostly Greek texts were recorded. The relevant texts comprise around 100 to 200 words. === Micro corpora === There are a significant number of ancient micro-corpus languages. Estimating the total number of attested ancient languages may be as difficult as estimating their corpus size. For example, Greek and Latin sources hand down an enormous amount of foreign-language glosses, the seriousness of which is not always certain. == Preservation and curation == Historic preservation and maintaining ancient text corpora presents several challenges, including issues with preservation, translation, and digitization. Many ancient texts have been lost over time, and those that survive may be damaged or fragmented. Translating ancient languages and scripts requires specialized expertise, and digitizing texts can be time-consuming and resource-intensive. == Corpus linguistics == The field of corpus linguistics studies language as expressed in text corpora. This includes the analysis of word frequency, collocations, grammar, and semantics. Ancient text corpora provide a valuable resource for corpus linguistics research, enabling scholars to explore the evolution of language and culture over time.

    Read more →
  • AI Background Removers Reviews: What Actually Works in 2026

    AI Background Removers Reviews: What Actually Works in 2026

    Trying to pick the best AI background remover? An AI background remover is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI background remover slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.

    Read more →
  • Babak Hodjat

    Babak Hodjat

    Babak Hodjat (Persian: بابک حجت; born November 1, 1967) is a British computer scientist, entrepreneur, and writer. He was the co-founder and CEO of Sentient Technologies and now holds the position of Chief Technology Officer AI at Cognizant. He is a specialist in the field of artificial intelligence and machine learning. In 1998 Hodjat co-founded Dejima Inc and served as CEO and CTO, his patented work on artificial intelligence led to the technology used by Apple for their digital assistant Siri. == Biography == === Early life === Babak Hodjat was born on November 1, 1967, in Wimbledon. His father was a retired university professor in entomology who worked at the British Museum. As a child, he did not like insects and would wander off to the nearby science museum, where he would spend long hours in front of a computer they had on display. He attended middle school in the United States. He studied at the Sharif University of Technology from 1986 to 1995, and received his Master of Science degree in software engineering. In 1994, together with another computer department student Hormoz Shahrzad presented their research titled Introducing a dynamic problem solving scheme based on a learning algorithm in artificial life environments at the first IEEE Conference on Computational Intelligence held at Orlando. Hodjat received a PhD in machine intelligence from Kyushu University in 2003 During his time there, he published several works on adaptive agent oriented software architecture and natural language user interfaces. === Career in science and business === Hodjat moved to Silicon Valley, California in 1998 and founded Dejima Inc. (named after the historic Japanese Dejima artificial island). The firm was based on a patented adaptive agent-oriented software engineering platform developed by Hodjat, Christopher Savoie and Makoto Amamiya. Hodjat served as the CTO and as the CEO for 9 months from October 2000. By 2000 the company had offices in San Jose, London and Tokyo. In 2002, the company developed a voice control Natural Interaction Platform (NPI) in collaboration with the Stanford University's research group Archimedes Project. During these years Hodjat continued his research on agent oriented software architecture and natural language user interfaces. In July 2003, Dejima got funding from SRI International within the Cognitive Assistant that Learns and Organizes (CALO) project of DARPA and worked on a Perceptive Assistant that Learns (PAL) initiative. Hodjat was the primary inventor of the firm's agent-oriented technology applied to intelligent interfaces for mobile and enterprise computing – a technology that eventually led to Siri. In April 2004, Dejima was acquired by Sybase iAnywhere. Hodjat served as senior director of engineering at Sybase iAnywhere from 2004 to 2008, where he developed AvantGo Platform, mBusiness Anywhere, and Answers Anywhere. In 2006, he co-founded MobileVerbs Inc., a mobile marketing service company, which was acquired by iLoop Mobile in February 2010. In 2007, he teamed with Antoine Blondeau (former CEO of Dejima) and Adam Cheyer (Dejima's vice president and Chief Architect of the CALO project) to establish Genetic Finance Holding Ltd. (where he began as CTO). In 2014 the firm became Sentient Technologies. Hodjat was joined by his long-time research fellow Hormoz Shahrzad who became principal scientist, while Hodjat held the position of chief scientist. In the following years Hodjat has worked on developing massively distributed computing technology and improving machine-learning technique known as evolutionary algorithms. One area that gained special attention from the press was applying Sentient Technologies algorithms to a stock market trading through specially created Sentient Investment Management hedge fund. Following the management change within Sentient Technologies, Hodjat became the company's CEO in February 2017. He continues his business and educational projects (he was on the jury of IBM Watson AI XPRIZE and the Merit Awards committee for the ISAL Award). == Writing == Hodjat is the author of multiple books such as The Konar and the Apple: Fun, Beauty, and Dread--From Ahwaz to California and the science fiction novel "The Narrator" (January 2022; ISBN 978-1-7354860-1-7)(March 2023; ISBN 978-1-7354860-0-0). == Selected publications == Hodjat, B.; Shahrzad, H. (1994). "Introducing a dynamic problem solving scheme based on a learning algorithm in artificial life environments". IEEE International Joint Conference on neural networks (IJCNN-94). Vol. 4. IEEE International Joint Conference on neural networks. pp. 2333–2338. doi:10.1109/ICNN.1994.374583. ISBN 978-0-7803-1901-1. S2CID 60497133. Hodjat, B.; Savoie, C.J.; Amamiya, M. (2006) [1998]. "An adaptive agent oriented software architecture". PRICAI'98: Topics in Artificial Intelligence. Springer. pp. 33–46. arXiv:cs/9812014. doi:10.1007/BFb0095256. ISBN 978-3-540-49461-4. S2CID 5317786. Hodjat, B.; Amamiya, M. (2000-05-25). "Applying the Adaptive Agent Oriented Software Architecture to the Parsing of Context Sensitive Grammars". IEICE Transactions on Information and Systems. E83-D (5): 1142–1152. ISSN 0916-8532. Retrieved 2017-12-14. Hodjat, Babak; Hodjat, Siamak; Treadgold, Nick; Jonsson, Ing-Marie (2006). "CRUSE: a context reactive natural language mobile interface". Proceedings of the 2nd annual international workshop on Wireless internet. WICON. doi:10.1145/1234161.1234181. ISBN 978-1-59593-510-6. S2CID 2388254. O'Reilly, Una-May; Wagy, Mark; Hodjat, Babak (2013). "Chapter 6: EC-Star: A Massive-Scale, Hub and Spoke, Distributed Genetic Programming System". In Riolo, R.; Vladislavleva, E.; Ritchie, M.; Moore, J.H. (eds.). Genetic Programming Theory and Practice X. Springer-Verlag New York. pp. 73–85. doi:10.1007/978-1-4614-6846-2. ISBN 978-1-4614-6845-5. S2CID 39650969. Retrieved 2017-12-14. Hodjat, Babak; Hemberg, Erik; Shahrzad, Hormoz; O'Reilly, Una-May (2014). "Chapter 4: Maintenance of a Long Running Distributed Genetic Programming System for Solving Problems Requiring Big Data". In Riolo, Rick; Moore, Jason H.; Kotanchek, Mark (eds.). Genetic Programming Theory and Practice XI. Springer-Verlag New York. pp. 65–83. doi:10.1007/978-1-4939-0375-7. ISBN 978-1-4939-0374-0. S2CID 28843739. Retrieved 2017-12-14. Shahrzad, Hormoz; Hodjat, Babak; Miikkulainen, Risto (2016). "Estimating the Advantage of Age-Layering in Evolutionary Algorithms". Proceedings of the Genetic and Evolutionary Computation Conference 2016. Genetic and Evolutionary Computation Conference. pp. 693–699. doi:10.1145/2908812.2908911. ISBN 978-1-4503-4206-3. S2CID 215516530. == Patents == Babak Hodjat holds 21 patents in the fields of agent-oriented programming, natural language decision engines, distributed evolutionary algorithms for asset management and trading and data mining.

    Read more →
  • SeaTable

    SeaTable

    SeaTable is a no-code platform that allows users to develop and implement business processes. The cloud collaboration service SeaTable is marketed by the GmbH of the same name with headquarters in Mainz and additional offices in Berlin and Beijing, and developed by the same company as Seafile. == History == SeaTable is a collaborative database and low-code application platform developed as part of a joint venture between Seafile Ltd., a software company based in Guangzhou, China, and SeaTable GmbH, a German firm headquartered in Mainz. Founded in 2020, the project represents the international expansion of Seafile, a Chinese developer originally known for its file synchronization and sharing software. While SeaTable's cloud services and European client operations are managed by the German entity, the platform itself is developed in China by Seafile's engineering team. This cross-border structure, described by TechCrunch as an “unconventional path” for a Chinese startup expanding abroad, reflects Seafile's effort to maintain its product development in China while addressing growing scrutiny in Western markets over data governance and corporate control. In 2021, an innovation project led by the Cyber Innovation Hub at the IT School of the German Armed Forces started to evaluate the possibilities of a large-scale deployment at the German Armed Forces. The evaluation project is currently still ongoing. In 2022, SeaTable is optimizing its database backend to allow millions of records within one base in the future. The focus of development is increasingly on automation and visualization. In 2025, SeaTable introduced AI-powered automations with version 6. The update enabled the integration of large language models (LLMs) for text analysis and automated decision-making. SeaTable operates a self-hosted LLM on servers provided by Hetzner (Germany), while self-hosted deployments can connect to any compatible model. == Features == SeaTable combines the traditional capabilities of a spreadsheet such as Excel and supplements them with a wide range of functions for process automation and visualization as well as a fully comprehensive API. SeaTable is not a pure cloud solution, but can alternatively be installed on a private server and operated completely autonomously. In this way, the owner retains full control over their own data. The installation is done via Docker on a Linux server. == Security and privacy == While most no-code platforms exist only as SaaS solutions, SeaTable describes itself as a data-sparse European solution. While initially the SeaTable Cloud was hosted on Amazon AWS, the move to the German data centers of Swiss provider Exoscale then took place in May 2021. This was followed by the replacement of the Freshdesk cloud ticketing system with a self-hosted Zammad instance, and since April 2022 SeaTable has completely dispensed with all tracking cookies on its website.

    Read more →
  • Best AI Video Generators in 2026

    Best AI Video Generators in 2026

    Curious about the best AI video generator? An AI video generator is software that uses machine learning to help you get more done — it combines speed, accuracy, and an interface that just works. Hands-on testing shows real-world results vary, so a short free trial is the smartest way to decide. Whether you are a beginner or a pro, the right AI video generator slots into your workflow and pays for itself fast. Read on for hands-on impressions, pricing tiers, and the standout features that matter.

    Read more →
  • Heng Ji

    Heng Ji

    Heng Ji is a computer scientist who works on information extraction and natural language processing. She is well known for her work on joined named entity recognition and relation extraction, as well as for her work on cross-document event extraction. She has been coordinating the popular NIST TAC Knowledge Base Population task since 2010. She has been recognised as one of AI's 10 to watch by IEEE Intelligent Systems in 2013, and has won multiple awards, including a NSF Career Award in 2009, Google Research awards in 2009 and 2014, and an IBM Watson Faculty Award in 2012. == Education == Heng Ji obtained a Bachelor's and master's degree in Computational Linguistics from Tsinghua University. She subsequently obtained a MSc, then PhD in Computer Science from New York University in 2008 under the supervision of Ralph Grishman. Her PhD thesis was on the topic of information extraction, with a particular focus on joint training of multiple components in the information extraction pipeline, as well as cross-lingual learning. == Career == Upon graduating with a PhD from New York University, Ji took up a position as assistant professor at Queens College, City University of New York, where she founded the BLENDER Lab, which focuses on research on cross-lingual, cross-documents, cross-media information extraction and fusion. In 2013, she joined Rensselaer Polytechnic Institute as an Edward P. Hamilton Development Chair and Tenured associate professor in Computer Science. Since 2019, she has been a full professor at the University of Illinois at Urbana–Champaign, as well as an Amazon Scholar. == Research == Heng Ji works in the area of natural language processing, machine learning and information extraction. She has published over 300 peer-reviewed research papers. Her work is published in the proceedings of computer science conferences, including the Annual Meeting of the Association for Computational Linguistics, The Web Conference, and the ACM Conference on Knowledge Discovery and Data Mining (KDD). Ji is a leading researcher in information extraction, having coordinated the popular NIST TAC Knowledge Base Population shared task since 2010. She is most recognised for her work on modelling interactions between subtasks in information extraction, which was also the topic of her PhD thesis, and for her work on event detection using cross-document signals. == Selected honors and distinctions == 2009 NSF Career Award 2009 Google Research Award 2012 IBM Watson Faculty Award 2013 IEEE AI's 10 to Watch 2014 Google Research Award 2016 World Economic Forum, 'Young Scientist' 2017 World Economic Forum, 'Young Scientist' 2020 Annual Meeting of the Association for Computational Linguistics, best demonstration paper

    Read more →
  • Top 10 AI Humanizers Compared (2026)

    Top 10 AI Humanizers Compared (2026)

    Looking for the best AI humanizer? An AI humanizer is software that uses machine learning to help you get more done — it can save you hours every week by automating repetitive work. Most options offer a generous free tier, with paid plans unlocking higher limits, faster processing, and team features. Whether you are a beginner or a pro, the right AI humanizer slots into your workflow and pays for itself fast. Read on for hands-on impressions, pricing tiers, and the standout features that matter.

    Read more →
  • Color vision

    Color vision

    Color vision (CV), a feature of visual perception, is an ability to perceive differences between light composed of different frequencies independently of light intensity. Color perception is a part of the larger visual system and is mediated by a complex process between neurons that begins with differential stimulation of different types of photoreceptors by light entering the eye. Those photoreceptors then emit outputs that are propagated through many layers of neurons ultimately leading to higher cognitive functions in the brain. Color vision is found in many animals and is mediated by similar underlying mechanisms with common types of biological molecules and a complex history of the evolution of color vision within different animal taxa. In primates, color vision may have evolved under selective pressure for a variety of visual tasks including the foraging for nutritious young leaves, ripe fruit, and flowers, as well as detecting predator camouflage and emotional states in other primates. == Wavelength == Isaac Newton discovered that white light after being split into its component colors when passed through a dispersive prism could be recombined to make white light by passing them through a different prism. The visible light spectrum ranges from about 380 to 740 nanometers. Spectral colors (colors that are produced by a narrow band of wavelengths) such as red, orange, yellow, green, cyan, blue, and violet can be found in this range. These spectral colors do not refer to a single wavelength, but rather to a set of wavelengths: red, 625–740 nm; orange, 590–625 nm; yellow, 565–590 nm; green, 500–565 nm; cyan, 485–500 nm; blue, 450–485 nm; violet, 380–450 nm. Wavelengths longer or shorter than this range are called infrared or ultraviolet, respectively. Humans cannot generally see these wavelengths, but other animals may. === Hue detection === Sufficient differences in wavelength cause a difference in the perceived hue; the just-noticeable difference in wavelength varies from about 1 nm in the blue-green and yellow wavelengths to 10 nm and more in the longer red and shorter blue wavelengths. Although the human eye can distinguish up to a few hundred hues, when those pure spectral colors are mixed together or diluted with white light, the number of distinguishable chromaticities can be much higher. In very low light levels, vision is scotopic: light is detected by rod cells of the retina. Rods are maximally sensitive to wavelengths near 500 nm and play little, if any, role in color vision. In brighter light, such as daylight, vision is photopic: light is detected by cone cells which are responsible for color vision. Cones are sensitive to a range of wavelengths, but are most sensitive to wavelengths near 555 nm. Between these regions, mesopic vision comes into play and both rods and cones provide signals to the retinal ganglion cells. The shift in color perception from dim light to daylight gives rise to differences known as the Purkinje effect. The perception of "white" is formed by the entire spectrum of visible light, or by mixing colors of just a few wavelengths in animals with few types of color receptors. In humans, white light can be perceived by combining wavelengths such as red, green, and blue, or just a pair of complementary colors such as blue and yellow. === Non-spectral colors === There are a variety of colors in addition to spectral colors and their hues. These include grayscale colors, shades of colors obtained by mixing grayscale colors with spectral colors, violet-red colors, impossible colors, and metallic colors. Grayscale colors include white, gray, and black. Rods contain rhodopsin, which reacts to light intensity, providing grayscale coloring. Shades include colors such as pink or brown. Pink is obtained from mixing red and white. Brown may be obtained from mixing orange with gray or black. Navy is obtained from mixing blue and black. Violet-red colors include hues and shades of magenta. The light spectrum is a line on which violet is one end and the other is red, and yet we see hues of purple that connect those two colors. Impossible colors are a combination of cone responses that cannot be naturally produced. For example, medium cones cannot be activated completely on their own; if they were, we would see a 'hyper-green' color. == Dimensionality == Color vision is categorized foremost according to the dimensionality of the color gamut, which is defined by the number of primaries required to represent the color vision. This is generally equal to the number of photopsins expressed: a correlation that holds for vertebrates but not invertebrates. The common vertebrate ancestor possessed four photopsins (expressed in cones) plus rhodopsin (expressed in rods), so was tetrachromatic. However, many vertebrate lineages have lost one or many photopsin genes, leading to lower-dimension color vision. The dimensions of color vision range from 1-dimensional and up: == Physiology of color perception == Perception of color begins with specialized retinal cells known as cone cells. Cone cells contain different forms of opsin – a pigment protein – that have different spectral sensitivities. Humans contain three types, resulting in trichromatic color vision. Each individual cone contains pigments composed of opsin apoprotein covalently linked to a light-absorbing prosthetic group: either 11-cis-hydroretinal or, more rarely, 11-cis-dehydroretinal. The cones are conventionally labeled according to the ordering of the wavelengths of the peaks of their spectral sensitivities: short (S), medium (M), and long (L) cone types. These three types do not correspond well to particular colors as we know them. Rather, the perception of color is achieved by a complex process that starts with the differential output of these cells in the retina and which is finalized in the visual cortex and associative areas of the brain. For example, while the L cones have been referred to simply as red receptors, microspectrophotometry has shown that their peak sensitivity is in the greenish-yellow region of the spectrum. Similarly, the S cones and M cones do not directly correspond to blue and green, although they are often described as such. The RGB color model, therefore, is a convenient means for representing color but is not directly based on the types of cones in the human eye. The peak response of human cone cells varies, even among individuals with typical color vision; in some non-human species this polymorphic variation is even greater, and it may well be adaptive. === Theories === Two complementary theories of color vision are the trichromatic theory and the opponent process theory. The trichromatic theory, or Young–Helmholtz theory, proposed in the 19th century by Thomas Young and Hermann von Helmholtz, posits three types of cones preferentially sensitive to blue, green, and red, respectively. Others have suggested that the trichromatic theory is not specifically a theory of color vision but a theory of receptors for all vision, including color but not specific or limited to it. Equally, it has been suggested that the relationship between the phenomenal opponency described by Ewald Hering and the physiological opponent processes are not straightforward (see below), making of physiological opponency a mechanism that is relevant to the whole of vision, and not just to color vision alone. Hering proposed the opponent process theory in 1872. It states that the visual system interprets color in an antagonistic way: red vs. green, blue vs. yellow, black vs. white. Both theories are generally accepted as valid, describing different stages in visual physiology, visualized in the adjacent diagram. Green–magenta and blue–yellow are scales with mutually exclusive boundaries. In the same way that there cannot exist a "slightly negative" positive number, a single eye cannot perceive a bluish-yellow or a reddish-green. Although these two theories are both currently widely accepted theories, past and more recent work has led to criticism of the opponent process theory, stemming from a number of what are presented as discrepancies in the standard opponent process theory. For example, the phenomenon of an after-image of complementary color can be induced by fatiguing the cells responsible for color perception, by staring at a vibrant color for a length of time, and then looking at a white surface. This phenomenon of complementary colors shows that cyan, rather than green, is the complement of red, and that magenta, rather than red, is the complement of green. It therefore also shows that the reddish-green color supposed to be impossible by opponent process theory is actually the color yellow. Although this phenomenon is more readily explained by the trichromatic theory, explanations for the discrepancy may include alterations to the opponent process theory, such as redefining the opponent colors as red vs. cyan, to reflect this effect. Despite such criticis

    Read more →
  • Indic OCR

    Indic OCR

    Indic OCR refers to the process of converting text images written in Indic scripts into e-text using Optical character recognition (OCR) techniques. Broadly, it can also refer to the OCR systems of Brahmic scripts for languages of South Asia and Southeast Asia, not just the scripts of the Indian subcontinent, which are all written in an abugida-based writing system. OCR for Latin characters is still not 100% accurate but a relatively high degree of accuracy in conversion has been able to be achieved. Such accuracy has not yet been able to be achieved for Indic scripts using OCR. This is due in part to the writing systems of Indic languages as well as a lack of standard representation, encoding, and support among operating systems and keyboards. The Centre for Development of Advanced Computing (C-DAC) and Technology Development for Indian Languages, the premier R&D organisation of the Ministry of Electronics and Information Technology (also known as MeitY) of India have carried out many projects relating to OCR. Their projects include OCR for Malayalam, Odia, Punjabi, Telugu and Devanagari script. == Properties of Indian writing systems == There are 22 officially recognised languages in India. Of these, Hindi, Bengali and Punjabi are the most widely spoken Indo-Aryan languages and are also the fourth, seventh and tenth most widely spoken languages in the world respectively. Two or more languages can be written with same script. For example, Devanagari is used to write Hindi, Marathi, Rajasthani, Sanskrit, Bhojpuri and others, while Eastern Nagari is used to write Bengali, Assamese, Manipuri and others. Apart from basic characters as consonants and vowels, most Indic languages combine 2 or more basic characters to form compound characters. The shape of a compound character is more complex than the constituent basic characters. Some Indo-Aryan languages (including Hindi and Punjabi) have a horizontal line over the characters, while other languages (including Gujarati) and Dravidian languages (Malayalam, Kannada, Tamil, and Telugu) do not. These are some of the main challenges for creating a single OCR for all Indic languages. Indic OCR also generally includes support for recently invented scripts in India like Ol Chiki, Warang Citi, Mundari Bani, etc. which are mainly created for writing Munda languages of Austroasiatic family. The concept of upper/lower case is absent in Indic scripts. Apart from Urdu, Sindhi, Kashmiri and Thaana, all other Indic languages are written from left to right. == Examples == SanskritOCR - OCR software for Sanskrit, Hindi and other Indo-Aryan languages based on the Devanagari script. Sanskrit OCR is developed by a Sanskrit scholar from Germany - Dr. Oliver Hellwig of Department for Languages and Cultures of Southern Asia, Freie Universität Berlin. The official website is in German. The interface of earlier versions of the software was also in German, but later versions have an English interface too. E-aksharayan - Optical character recognition engine for Indian languages Chitrankan - This technology was developed by ISI, Kolkata, and transferred to C-DAC. It processes printed Hindi text from a scanner or from an image. Indic OCR models for Tesseract (software) == OCR in use == OCR has been used for Wikisource and other projects.

    Read more →
  • Erkki Oja

    Erkki Oja

    Erkki Oja (born 22 March 1948) is a Finnish computer scientist and Aalto Distinguished Professor in the Department of Information and Computer Science at Aalto University School of Science. He is recognized for developing Oja's rule, which is a model of how neurons in the brain or in artificial neural networks learn over time. == Early life and education == Oja was born in Helsinki and studied at Helsinki University of Technology, where he received his diploma engineer in 1972, licentiate in technology in 1975 and Doctor of Technology in 1977. == Career == Oja was a research associate at the Center for Cognitive Science at Brown University between 1977 and 1978 and a research fellow at the Academy of Finland from 1976 to 1981. Since 1981, he took up a professorship in applied mathematics at Kuopio University (now University of Eastern Finland). He was a visiting research scholar at Tokyo Institute of Technology from 1983 to 1984. From 1987 to 1993, he was a professor in computer science at the Lappeenranta University of Technology. He moved back to the Helsinki University of Technology (now Aalto University) from 1993 as a professor in computer science. He retired in 2015. == Honors and awards == Oja is a Fellow of the International Association for Pattern Recognition and the IEEE, and a member of the Finnish Academy of Sciences. He served as chairman of the European Neural Network Society between 2000 and 2005, and as the chairman of the Academy of Finland’s Research Council for Natural Sciences and Engineering between 2007 and 2012. He was awarded the Frank Rosenblatt Award for his contributions to artificial intelligence research in 2019. Oja was a member of the Board of Governors for the International Neural Network Society (INNIS) in 2003. He received honorary doctorates from Uppsala University and Lappeenranta University of Technology in 2008.

    Read more →
  • Dynamic topic model

    Dynamic topic model

    Within statistics, Dynamic topic models' are generative models that can be used to analyze the evolution of (unobserved) topics of a collection of documents over time. This family of models was proposed by David Blei and John Lafferty and is an extension to Latent Dirichlet Allocation (LDA) that can handle sequential documents. In LDA, both the order the words appear in a document and the order the documents appear in the corpus are oblivious to the model. Whereas words are still assumed to be exchangeable, in a dynamic topic model the order of the documents plays a fundamental role. More precisely, the documents are grouped by time slice (e.g.: years) and it is assumed that the documents of each group come from a set of topics that evolved from the set of the previous slice. == Topics == Similarly to LDA and pLSA, in a dynamic topic model, each document is viewed as a mixture of unobserved topics. Furthermore, each topic defines a multinomial distribution over a set of terms. Thus, for each word of each document, a topic is drawn from the mixture and a term is subsequently drawn from the multinomial distribution corresponding to that topic. The topics, however, evolve over time. For instance, the two most likely terms of a topic at time t could be "network" and "Zipf" (in descending order) while the most likely ones at time t+1 could be "Zipf" and "percolation" (in descending order). == Model == Define α t {\displaystyle \alpha _{t}} as the per-document topic distribution at time t. β t , k {\displaystyle \beta _{t,k}} as the word distribution of topic k at time t. η t , d {\displaystyle \eta _{t,d}} as the topic distribution for document d in time t, z t , d , n {\displaystyle z_{t,d,n}} as the topic for the nth word in document d in time t, and w t , d , n {\displaystyle w_{t,d,n}} as the specific word. In this model, the multinomial distributions α t + 1 {\displaystyle \alpha _{t+1}} and β t + 1 , k {\displaystyle \beta _{t+1,k}} are generated from α t {\displaystyle \alpha _{t}} and β t , k {\displaystyle \beta _{t,k}} , respectively. Even though multinomial distributions are usually written in terms of the mean parameters, representing them in terms of the natural parameters is better in the context of dynamic topic models. The former representation has some disadvantages due to the fact that the parameters are constrained to be non-negative and sum to one. When defining the evolution of these distributions, one would need to assure that such constraints were satisfied. Since both distributions are in the exponential family, one solution to this problem is to represent them in terms of the natural parameters, that can assume any real value and can be individually changed. Using the natural parameterization, the dynamics of the topic model are given by β t , k | β t − 1 , k ∼ N ( β t − 1 , k , σ 2 I ) {\displaystyle \beta _{t,k}|\beta _{t-1,k}\sim N(\beta _{t-1,k},\sigma ^{2}I)} and α t | α t − 1 ∼ N ( α t − 1 , δ 2 I ) {\displaystyle \alpha _{t}|\alpha _{t-1}\sim N(\alpha _{t-1},\delta ^{2}I)} . The generative process at time slice 't' is therefore: Draw topics β t , k | β t − 1 , k ∼ N ( β t − 1 , k , σ 2 I ) ∀ k {\displaystyle \beta _{t,k}|\beta _{t-1,k}\sim N(\beta _{t-1,k},\sigma ^{2}I)\forall k} Draw mixture model α t | α t − 1 ∼ N ( α t − 1 , δ 2 I ) {\displaystyle \alpha _{t}|\alpha _{t-1}\sim N(\alpha _{t-1},\delta ^{2}I)} For each document: Draw η t , d ∼ N ( α t , a 2 I ) {\displaystyle \eta _{t,d}\sim N(\alpha _{t},a^{2}I)} For each word: Draw topic Z t , d , n ∼ Mult ( π ( η t , d ) ) {\displaystyle Z_{t,d,n}\sim {\textrm {Mult}}(\pi (\eta _{t,d}))} Draw word W t , d , n ∼ Mult ( π ( β t , Z t , d , n ) ) {\displaystyle W_{t,d,n}\sim {\textrm {Mult}}(\pi (\beta _{t,Z_{t,d,n}}))} where π ( x ) {\displaystyle \pi (x)} is a mapping from the natural parameterization x to the mean parameterization, namely π ( x i ) = exp ⁡ ( x i ) ∑ i exp ⁡ ( x i ) {\displaystyle \pi (x_{i})={\frac {\exp(x_{i})}{\sum _{i}\exp(x_{i})}}} . == Inference == In the dynamic topic model, only W t , d , n {\displaystyle W_{t,d,n}} is observable. Learning the other parameters constitutes an inference problem. Blei and Lafferty argue that applying Gibbs sampling to do inference in this model is more difficult than in static models, due to the nonconjugacy of the Gaussian and multinomial distributions. They propose the use of variational methods, in particular, the Variational Kalman Filtering and the Variational Wavelet Regression. == Applications == In the original paper, a dynamic topic model is applied to the corpus of Science articles published between 1881 and 1999 aiming to show that this method can be used to analyze the trends of word usage inside topics. The authors also show that the model trained with past documents is able to fit documents of an incoming year better than LDA. A continuous dynamic topic model was developed by Wang et al. and applied to predict the timestamp of documents. Going beyond text documents, dynamic topic models were used to study musical influence, by learning musical topics and how they evolve in recent history.

    Read more →
  • Decision list

    Decision list

    Decision lists are a representation for Boolean functions which can be easily learned from examples. Single term decision lists are more expressive than disjunctions and conjunctions; however, 1-term decision lists are less expressive than the general disjunctive normal form and the conjunctive normal form. The language specified by a k-length decision list includes as a subset the language specified by a k-depth decision tree. Learning decision lists can be used for attribute efficient learning, a type of machine learning. == Definition == A decision list (DL) of length r is of the form: if f1 then output b1 else if f2 then output b2 ... else if fr then output br where fi is the ith formula and bi is the ith boolean for i ∈ { 1... r } {\displaystyle i\in \{1...r\}} . The last if-then-else is the default case, which means formula fr is always equal to true. A k-DL is a decision list where all of formulas have at most k terms. Sometimes "decision list" is used to refer to a 1-DL, where all of the formulas are either a variable or its negation.

    Read more →
  • AI Video Editors: Free vs Paid (2026)

    AI Video Editors: Free vs Paid (2026)

    Trying to pick the best AI video editor? An AI video editor is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI video editor slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.

    Read more →
  • Unsupervised learning

    Unsupervised learning

    Unsupervised learning is a framework in machine learning where, in contrast to supervised learning, algorithms learn patterns exclusively from unlabeled data. Other frameworks in the spectrum of supervisions include weak- or semi-supervision, where a small portion of the data is tagged, and self-supervision. Some researchers consider self-supervised learning a form of unsupervised learning. Conceptually, unsupervised learning divides into the aspects of data, training, algorithm, and downstream applications. Typically, the dataset is harvested cheaply "in the wild", such as massive text corpus obtained by web crawling, with only minor filtering (such as Common Crawl). This compares favorably to supervised learning, where the dataset (such as the ImageNet1000) is typically constructed manually, which is much more expensive. There are algorithms designed specifically for unsupervised learning, such as clustering algorithms like k-means, dimensionality reduction techniques like principal component analysis (PCA), Boltzmann machine learning, and autoencoders. After the rise of deep learning, most large-scale unsupervised learning has been done by training general-purpose neural network architectures by gradient descent, adapted to performing unsupervised learning by designing an appropriate training procedure. Sometimes a trained model can be used as-is, but more often they are modified for downstream applications. For example, the generative pretraining method trains a model to generate a textual dataset, before finetuning it for other applications, such as text classification. As another example, autoencoders are trained to produce good features, which can then be used as a module for other models, such as in a latent diffusion model. == Tasks == Tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see Venn diagram); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups. Furthermore, as progress marches onward, some tasks employ both methods, and some tasks swing from one to another. For example, image recognition started off as heavily supervised, but became hybrid by employing unsupervised pre-training, and then moved towards supervision again with the advent of dropout, ReLU, and adaptive learning rates. A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and the model must infer the removed part. This is particularly clear for the denoising autoencoders and BERT. == Neural network architectures == === Training === During the learning phase, an unsupervised network tries to mimic the data it is given and uses the error in its mimicked output to correct itself (i.e. correct its weights and biases). Sometimes the error is expressed as a low probability that the erroneous output occurs, or it might be expressed as an unstable high energy state in the network. In contrast to supervised methods' dominant use of backpropagation, unsupervised learning also employs other methods including: Hopfield learning rule, Boltzmann learning rule, Contrastive Divergence, Wake Sleep, Variational Inference, Maximum Likelihood, Maximum A Posteriori, Gibbs Sampling, and backpropagating reconstruction errors or hidden state reparameterizations. See the table below for more details. === Energy === An energy function is a macroscopic measure of a network's activation state. In Boltzmann machines, it plays the role of the Cost function. This analogy with physics is inspired by Ludwig Boltzmann's analysis of a gas' macroscopic energy from the microscopic probabilities of particle motion p ∝ e − E / k T {\displaystyle p\propto e^{-E/kT}} , where k is the Boltzmann constant and T is temperature. In the RBM network the relation is p = e − E / Z {\displaystyle p=e^{-E}/Z} , where p {\displaystyle p} and E {\displaystyle E} vary over every possible activation pattern and Z = ∑ All Patterns e − E ( pattern ) {\displaystyle \textstyle {Z=\sum _{\scriptscriptstyle {\text{All Patterns}}}e^{-E({\text{pattern}})}}} . To be more precise, p ( a ) = e − E ( a ) / Z {\displaystyle p(a)=e^{-E(a)}/Z} , where a {\displaystyle a} is an activation pattern of all neurons (visible and hidden). Hence, some early neural networks bear the name Boltzmann Machine. Paul Smolensky calls − E {\displaystyle -E\,} the Harmony. A network seeks low energy which is high Harmony. === Networks === This table shows connection diagrams of various unsupervised networks, the details of which will be given in the section Comparison of Networks. Circles are neurons and edges between them are connection weights. As network design changes, features are added on to enable new capabilities or removed to make learning faster. For instance, neurons change between deterministic (Hopfield) and stochastic (Boltzmann) to allow robust output, weights are removed within a layer (RBM) to hasten learning, or connections are allowed to become asymmetric (Helmholtz). Of the networks bearing people's names, only Hopfield worked directly with neural networks. Boltzmann and Helmholtz came before artificial neural networks, but their work in physics and physiology inspired the analytical methods that were used. === History === === Specific Networks === Here, we highlight some characteristics of select networks. The details of each are given in the comparison table below. Hopfield Network Ferromagnetism inspired Hopfield networks. A neuron corresponds to an iron domain with binary magnetic moments Up and Down, and neural connections correspond to the domain's influence on each other. Symmetric connections enable a global energy formulation. During inference the network updates each state using the standard activation step function. Symmetric weights and the right energy functions guarantees convergence to a stable activation pattern. Asymmetric weights are difficult to analyze. Hopfield nets are used as Content Addressable Memories (CAM). Boltzmann Machine These are stochastic Hopfield nets. Their state value is sampled from this pdf as follows: suppose a binary neuron fires with the Bernoulli probability p(1) = 1/3 and rests with p(0) = 2/3. One samples from it by taking a uniformly distributed random number y, and plugging it into the inverted cumulative distribution function, which in this case is the step function thresholded at 2/3. The inverse function = { 0 if x <= 2/3, 1 if x > 2/3 }. Sigmoid Belief Net Introduced by Radford Neal in 1992, this network applies ideas from probabilistic graphical models to neural networks. A key difference is that nodes in graphical models have pre-assigned meanings, whereas Belief Net neurons' features are determined after training. The network is a sparsely connected directed acyclic graph composed of binary stochastic neurons. The learning rule comes from Maximum Likelihood on p(X): Δwij ∝ {\displaystyle \propto } sj (si - pi), where pi = 1 / ( 1 + eweighted inputs into neuron i ). sj's are activations from an unbiased sample of the posterior distribution and this is problematic due to the Explaining Away problem raised by Judea Perl. Variational Bayesian methods uses a surrogate posterior and blatantly disregard this complexity. Deep Belief Network Introduced by Hinton, this network is a hybrid of RBM and Sigmoid Belief Network. The top 2 layers is an RBM and the second layer downwards form a sigmoid belief network. One trains it by the stacked RBM method and then throw away the recognition weights below the top RBM. As of 2009, 3-4 layers seems to be the optimal depth. Helmholtz machine These are early inspirations for the Variational Auto Encoders. Its 2 networks combined into one—forward weights operates recognition and backward weights implements imagination. It is perhaps the first network to do both. Helmholtz did not work in machine learning but he inspired the view of "statistical inference engine whose function is to infer probable causes of sensory input". the stochastic binary neuron outputs a probability that its state is 0 or 1. The data input is normally not considered a layer, but in the Helmholtz machine generation mode, the data layer receives input from the middle layer and has separate weights for this purpose, so it is considered a layer. Hence this network has 3 layers. Variational autoencoder These are inspired by Helmholtz machines and combines probability network with neural networks. An Autoencoder is a 3-layer CAM network, where the middle layer is supposed to be some internal representation of input patterns. The encoder neural network is a probability distribution qφ(z given x) and the decoder network is pθ(x given z). The weights are named phi & theta rather than W and V as in Helmholtz—a cosmetic difference. These 2 networks h

    Read more →