AI Avatar Arbitrage

AI Avatar Arbitrage — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • CinePlayer

    CinePlayer

    CinePlayer is a software based media player used to review Digital Cinema Packages (DCP) without the need for a digital cinema server by Doremi Labs. CinePlayer can play back any DCP, not just those created by Doremi Mastering products. In addition to playing DCPs, CinePlayer can also playback JPEG2000 image sequences and many popular multimedia file types. There are two versions of CinePlayer available, standard and Pro. The standard version supports playback of non-encrypted, 2D DCP's up to 2K resolution. The Pro version supports playback of encrypted, 2D or 3D DCP's with subtitles up to 4K resolution. == Supported formats == === Containers === AVI MOV MXF MPG TS WMV M2TS MTS MP4 MKV === Video codecs === JPEG2000 ProRes 422 DNxHD YUV Uncompressed 8-10 bits DIVX XVID MPEG4 AVC / H-264 VC-1 MPEG2 === Supported image sequences === BMP TIFF TGA DPX JPG J2C === Supported audio files === WAV MP3 WMA MP2

    Read more →
  • Semiautomaton

    Semiautomaton

    In mathematics and theoretical computer science, a semiautomaton is a deterministic finite automaton having inputs but no output. It consists of a set Q of states, a set Σ called the input alphabet, and a function T: Q × Σ → Q called the transition function. Associated with any semiautomaton is a monoid called the characteristic monoid, input monoid, transition monoid or transition system of the semiautomaton, which acts on the set of states Q. This may be viewed either as an action of the free monoid of strings in the input alphabet Σ, or as the induced transformation semigroup of Q. In older books like Clifford and Preston (1967) semigroup actions are called "operands". In category theory, semiautomata essentially are functors. == Transformation semigroups and monoid acts == A transformation semigroup or transformation monoid is a pair ( M , Q ) {\displaystyle (M,Q)} consisting of a set Q (often called the "set of states") and a semigroup or monoid M of functions, or "transformations", mapping Q to itself. They are functions in the sense that every element m of M is a map m : Q → Q {\displaystyle m\colon Q\to Q} . If s and t are two functions of the transformation semigroup, their semigroup product is defined as their function composition ( s t ) ( q ) = ( s ∘ t ) ( q ) = s ( t ( q ) ) {\displaystyle (st)(q)=(s\circ t)(q)=s(t(q))} . Some authors regard "semigroup" and "monoid" as synonyms. Here a semigroup need not have an identity element; a monoid is a semigroup with an identity element (also called "unit"). Since the notion of functions acting on a set always includes the notion of an identity function, which when applied to the set does nothing, a transformation semigroup can be made into a monoid by adding the identity function. === M-acts === Let M be a monoid and Q be a non-empty set. If there exists a multiplicative operation μ : Q × M → Q {\displaystyle \mu \colon Q\times M\to Q} ( q , m ) ↦ q m = μ ( q , m ) {\displaystyle (q,m)\mapsto qm=\mu (q,m)} which satisfies the properties q 1 = q {\displaystyle q1=q} for 1 the unit of the monoid, and q ( s t ) = ( q s ) t {\displaystyle q(st)=(qs)t} for all q ∈ Q {\displaystyle q\in Q} and s , t ∈ M {\displaystyle s,t\in M} , then the triple ( Q , M , μ ) {\displaystyle (Q,M,\mu )} is called a right M-act or simply a right act. In long-hand, μ {\displaystyle \mu } is the right multiplication of elements of Q by elements of M. The right act is often written as Q M {\displaystyle Q_{M}} . A left act is defined similarly, with μ : M × Q → Q {\displaystyle \mu \colon M\times Q\to Q} ( m , q ) ↦ m q = μ ( m , q ) {\displaystyle (m,q)\mapsto mq=\mu (m,q)} and is often denoted as M Q {\displaystyle \,_{M}Q} . An M-act is closely related to a transformation monoid. However the elements of M need not be functions per se, they are just elements of some monoid. Therefore, one must demand that the action of μ {\displaystyle \mu } be consistent with multiplication in the monoid (i.e. μ ( q , s t ) = μ ( μ ( q , s ) , t ) {\displaystyle \mu (q,st)=\mu (\mu (q,s),t)} ), as, in general, this might not hold for some arbitrary μ {\displaystyle \mu } , in the way that it does for function composition. Once one makes this demand, it is completely safe to drop all parenthesis, as the monoid product and the action of the monoid on the set are completely associative. In particular, this allows elements of the monoid to be represented as strings of letters, in the computer-science sense of the word "string". This abstraction then allows one to talk about string operations in general, and eventually leads to the concept of formal languages as being composed of strings of letters. Another difference between an M-act and a transformation monoid is that for an M-act Q, two distinct elements of the monoid may determine the same transformation of Q. If we demand that this does not happen, then an M-act is essentially the same as a transformation monoid. === M-homomorphism === For two M-acts Q M {\displaystyle Q_{M}} and B M {\displaystyle B_{M}} sharing the same monoid M {\displaystyle M} , an M-homomorphism f : Q M → B M {\displaystyle f\colon Q_{M}\to B_{M}} is a map f : Q → B {\displaystyle f\colon Q\to B} such that f ( q m ) = f ( q ) m {\displaystyle f(qm)=f(q)m} for all q ∈ Q M {\displaystyle q\in Q_{M}} and m ∈ M {\displaystyle m\in M} . The set of all M-homomorphisms is commonly written as H o m ( Q M , B M ) {\displaystyle \mathrm {Hom} (Q_{M},B_{M})} or H o m M ( Q , B ) {\displaystyle \mathrm {Hom} _{M}(Q,B)} . The M-acts and M-homomorphisms together form a category called M-Act. == Semiautomata == A semiautomaton is a triple ( Q , Σ , T ) {\displaystyle (Q,\Sigma ,T)} where Σ {\displaystyle \Sigma } is a non-empty set, called the input alphabet, Q is a non-empty set, called the set of states, and T is the transition function T : Q × Σ → Q . {\displaystyle T\colon Q\times \Sigma \to Q.} When the set of states Q is a finite set—it need not be—, a semiautomaton may be thought of as a deterministic finite automaton ( Q , Σ , T , q 0 , A ) {\displaystyle (Q,\Sigma ,T,q_{0},A)} , but without the initial state q 0 {\displaystyle q_{0}} or set of accept states A. Alternately, it is a finite-state machine that has no output, and only an input. Any semiautomaton induces an act of a monoid in the following way. Let Σ ∗ {\displaystyle \Sigma ^{}} be the free monoid generated by the alphabet Σ {\displaystyle \Sigma } (so that the superscript is understood to be the Kleene star); it is the set of all finite-length strings composed of the letters in Σ {\displaystyle \Sigma } . For every word w in Σ ∗ {\displaystyle \Sigma ^{}} , let T w : Q → Q {\displaystyle T_{w}\colon Q\to Q} be the function, defined recursively, as follows, for all q in Q: If w = ε {\displaystyle w=\varepsilon } , then T ε ( q ) = q {\displaystyle T_{\varepsilon }(q)=q} , so that the empty word ε {\displaystyle \varepsilon } does not change the state. If w = σ {\displaystyle w=\sigma } is a letter in Σ {\displaystyle \Sigma } , then T σ ( q ) = T ( q , σ ) {\displaystyle T_{\sigma }(q)=T(q,\sigma )} . If w = σ v {\displaystyle w=\sigma v} for σ ∈ Σ {\displaystyle \sigma \in \Sigma } and v ∈ Σ ∗ {\displaystyle v\in \Sigma ^{}} , then T w ( q ) = T v ( T σ ( q ) ) {\displaystyle T_{w}(q)=T_{v}(T_{\sigma }(q))} . Let M ( Q , Σ , T ) {\displaystyle M(Q,\Sigma ,T)} be the set M ( Q , Σ , T ) = { T w | w ∈ Σ ∗ } . {\displaystyle M(Q,\Sigma ,T)=\{T_{w}\vert w\in \Sigma ^{}\}.} The set M ( Q , Σ , T ) {\displaystyle M(Q,\Sigma ,T)} is closed under function composition; that is, for all v , w ∈ Σ ∗ {\displaystyle v,w\in \Sigma ^{}} , one has T w ∘ T v = T v w {\displaystyle T_{w}\circ T_{v}=T_{vw}} . It also contains T ε {\displaystyle T_{\varepsilon }} , which is the identity function on Q. Since function composition is associative, the set M ( Q , Σ , T ) {\displaystyle M(Q,\Sigma ,T)} is a monoid: it is called the input monoid, characteristic monoid, characteristic semigroup or transition monoid of the semiautomaton ( Q , Σ , T ) {\displaystyle (Q,\Sigma ,T)} . == Properties == If the set of states Q is finite, then the transition functions are commonly represented as state transition tables. The structure of all possible transitions driven by strings in the free monoid has a graphical depiction as a de Bruijn graph. The set of states Q need not be finite, or even countable. As an example, semiautomata underpin the concept of quantum finite automata. There, the set of states Q are given by the complex projective space C P n {\displaystyle \mathbb {C} P^{n}} , and individual states are referred to as n-state qubits. State transitions are given by unitary n×n matrices. The input alphabet Σ {\displaystyle \Sigma } remains finite, and other typical concerns of automata theory remain in play. Thus, the quantum semiautomaton may be simply defined as the triple ( C P n , Σ , { U σ 1 , U σ 2 , … , U σ p } ) {\displaystyle (\mathbb {C} P^{n},\Sigma ,\{U_{\sigma _{1}},U_{\sigma _{2}},\dotsc ,U_{\sigma _{p}}\})} when the alphabet Σ {\displaystyle \Sigma } has p letters, so that there is one unitary matrix U σ {\displaystyle U_{\sigma }} for each letter σ ∈ Σ {\displaystyle \sigma \in \Sigma } . Stated in this way, the quantum semiautomaton has many geometrical generalizations. Thus, for example, one may take a Riemannian symmetric space in place of C P n {\displaystyle \mathbb {C} P^{n}} , and selections from its group of isometries as transition functions. The syntactic monoid of a regular language is isomorphic to the transition monoid of the minimal automaton accepting the language. == Literature == A. H. Clifford and G. B. Preston, The Algebraic Theory of Semigroups. American Mathematical Society, volume 2 (1967), ISBN 978-0-8218-0272-4. F. Gecseg and I. Peak, Algebraic Theory of Automata (1972), Akademiai Kiado, Budapest. W. M. L. Holcombe, Algebraic Automata Theory (1982), Cambridge University Press J. M. Howie, Automata and Languages, (1991), Cla

    Read more →
  • The Best Free AI Content Generator for Beginners

    The Best Free AI Content Generator for Beginners

    Looking for the best AI content generator? An AI content generator 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 content generator 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 →
  • Raymond J. Mooney

    Raymond J. Mooney

    Raymond J. Mooney is an American computer scientist, professor of computer science, and director of the Artificial Intelligence laboratory at the University of Texas at Austin. His research focuses on machine learning and natural language processing. He was educated at O'Fallon Township High School in O'Fallon, Illinois and earned a BS, MS, and Ph.D. in computer science at the University of Illinois at Urbana-Champaign, where he was advised by Gerald DeJong. He is a fellow of the Association for Computing Machinery (ACM), Association for Computational Linguistics (ACL), and Association for the Advancement of Artificial Intelligence (AAAI).

    Read more →
  • Pixel aspect ratio

    Pixel aspect ratio

    A pixel aspect ratio (PAR) is a mathematical ratio that describes how the width of a pixel in a digital image compares to the height of that pixel. Most digital imaging systems display an image as a grid of tiny, square pixels. However, some imaging systems, especially those that must be compatible with standard-definition television motion pictures, display an image as a grid of rectangular pixels, in which the pixel width and height are different. Pixel aspect ratio describes this difference. Use of pixel aspect ratio mostly involves pictures pertaining to standard-definition television and some other exceptional cases. Most other imaging systems, including those that comply with SMPTE standards and practices, use square pixels. PAR is also known as sample aspect ratio and abbreviated SAR, though it can be confused with storage aspect ratio. == Introduction == The ratio of the width to the height of an image is known as the aspect ratio, or more precisely the display aspect ratio (DAR) – the aspect ratio of the image as displayed; for TV, DAR was traditionally 4:3 (a.k.a. fullscreen), with 16:9 (a.k.a. widescreen) now the standard for HDTV. In digital images, there is a distinction with the storage aspect ratio (SAR), which is the ratio of pixel dimensions. If an image is displayed with square pixels, then these ratios agree; if not, then non-square, "rectangular" pixels are used, and these ratios disagree. The aspect ratio of the pixels themselves is known as the pixel aspect ratio (PAR) – for square pixels this is 1:1 – and these are related by the identity: Rearranging (solving for PAR) yields: For example: A 640 × 480 VGA image has a SAR of 640/480 = 4:3, and if displayed on a 4:3 display (DAR = 4:3) has square pixels, hence a PAR of 1:1. By contrast, a 720 × 576 D-1 PAL image has a SAR of 720/576 = 5:4, but if displayed on a 4:3 display (DAR = 4:3) the PAR is 4/3 : 5/4 = 16:15 ≈ 1.066. This means that the pixels of the PAL picture must be "stretched" by this amount to fit in the 4:3 display. In analog images such as film there is no notion of pixel, nor notion of SAR or PAR, but in the digitization of analog images the resulting digital image has pixels, hence SAR (and accordingly PAR, if displayed at the same aspect ratio as the original). Non-square pixels arise often in early digital TV standards, related to digitalization of analog TV signals – whose vertical and "effective" horizontal resolutions differ and are thus best described by non-square pixels – and also in some digital video cameras and computer display modes, such as Color Graphics Adapter (CGA). Today they arise also in transcoding between resolutions with different SARs. Actual displays do not generally have non-square pixels, though digital sensors might; they are rather a mathematical abstraction used in resampling images to convert between resolutions. There are several complicating factors in understanding PAR, particularly as it pertains to digitization of analog video: First, analog video does not have pixels, but rather a raster scan, and thus has a well-defined vertical resolution (the lines of the raster), but not a well-defined horizontal resolution, since each line is an analog signal. However, by a standardized sampling rate, the effective horizontal resolution can be determined by the sampling theorem, as is done below. Second, due to overscan, some of the lines at the top and bottom of the raster are not visible, as are some of the possible image on the left and right – see Overscan: Analog to digital resolution issues. Also, the resolution may be rounded (DV NTSC uses 480 lines, rather than the 486 that are possible). Third, analog video signals are interlaced – each image (frame) is sent as two "fields", each with half the lines. Thus either the pixels are twice as tall as they would be without interlacing, or the image is deinterlaced. == Background == Video is presented as a sequential series of images called video frames. Historically, video frames were created and recorded in analog form. As digital display technology, digital broadcast technology, and digital video compression evolved separately, it resulted in video frame differences that must be addressed using pixel aspect ratio. Digital video frames are generally defined as a grid of pixels used to present each sequential image. The horizontal component is defined by pixels (or samples), and is known as a video line. The vertical component is defined by the number of lines, as in 480 lines. Standard-definition television standards and practices were developed as broadcast technologies and intended for terrestrial broadcasting, and were therefore not designed for digital video presentation. Such standards define an image as an array of well-defined horizontal "Lines", well-defined vertical "Line Duration" and a well-defined picture center. However, there is not a standard-definition television standard that properly defines image edges or explicitly demands a certain number of picture elements per line. Furthermore, analog video systems such as NTSC 480i and PAL 576i, instead of employing progressively displayed frames, employ fields or interlaced half-frames displayed in an interwoven manner to reduce flicker and double the image rate for smoother motion. === Analog-to-digital conversion === As a result of computers becoming powerful enough to serve as video editing tools, video digital-to-analog converters and analog-to-digital converters were made to overcome this incompatibility. To convert analog video lines into a series of square pixels, the industry adopted a default sampling rate at which luma values were extracted into pixels. The luma sampling rate for 480i pictures was 12+3⁄11 MHz and for 576i pictures was 14+3⁄4 MHz. The term pixel aspect ratio was first coined when ITU-R BT.601 (commonly known as Rec. 601) specified that standard-definition television pictures are made of lines of exactly 720 non-square pixels. ITU-R BT.601 did not define the exact pixel aspect ratio but did provide enough information to calculate the exact pixel aspect ratio based on industry practices: The standard luma sampling rate of precisely 13+1⁄2 MHz. Based on this information: The pixel aspect ratio for 480i would be 10:11 as: 12 3 11 ÷ 13 1 2 = 10 11 {\displaystyle 12{\tfrac {3}{11}}\div 13{\tfrac {1}{2}}={\tfrac {10}{11}}} The pixel aspect ratio for 576i would be 59:54 as: 14 3 4 ÷ 13 1 2 = 59 54 {\displaystyle 14{\tfrac {3}{4}}\div 13{\tfrac {1}{2}}={\tfrac {59}{54}}} SMPTE RP 187 further attempted to standardize the pixel aspect ratio values for 480i and 576i. It designated 177:160 for 480i or 1035:1132 for 576i. However, due to significant difference with practices in effect by industry and the computational load that they imposed upon the involved hardware, SMPTE RP 187 was simply ignored. SMPTE RP 187 information annex A.4 further suggested the use of 10:11 for 480i. As of this writing, ITU-R BT.601-6, which is the latest edition of ITU-R BT.601, still implies that the pixel aspect ratios mentioned above are correct. === Digital video processing === As stated above, ITU-R BT.601 specified that standard-definition television pictures are made of lines of 720 non-square pixels, sampled with a precisely specified sampling rate. A simple mathematical calculation reveals that a 704 pixel width would be enough to contain a 480i or 576i standard 4:3 picture: A 4:3 480-line picture, digitized with the Rec. 601-recommended sampling rate, would be 704 non-square pixels wide. x 480 × 10 11 = 4 3 ⇒ x = 480 × 11 × 4 10 × 3 = 704 {\displaystyle {\frac {x}{480}}\times {\frac {10}{11}}={\frac {4}{3}}\Rightarrow x={\frac {480\times 11\times 4}{10\times 3}}=704} A 4:3 576-line picture, digitized with the Rec. 601-recommended sampling rate, would be 702+54⁄59 non-square pixels wide. x 576 × 59 54 = 4 3 ⇒ x = 576 × 54 × 4 59 × 3 = 702 54 59 {\displaystyle {\frac {x}{576}}\times {\frac {59}{54}}={\frac {4}{3}}\Rightarrow x={\frac {576\times 54\times 4}{59\times 3}}=702{\tfrac {54}{59}}} Unfortunately, not all standard TV pictures are exactly 4:3: As mentioned earlier, in analog video, the center of a picture is well-defined but the edges of the picture are not standardized. As a result, some analog devices (mostly PAL devices but also some NTSC devices) generated motion pictures that were horizontally (slightly) wider. This also proportionately applies to anamorphic widescreen (16:9) pictures. Therefore, to maintain a safe margin of error, ITU-R BT.601 required sampling 16 more non-square pixels per line (8 more at each edge) to ensure saving all video data near the margins. This requirement, however, had implications for PAL motion pictures. PAL pixel aspect ratios for standard (4:3) and anamorphic wide screen (16:9), respectively 59:54 and 118:81, were awkward for digital image processing, especially for mixing PAL and NTSC video clips. Therefore, video editing products chose the almost equivalent value

    Read more →
  • Best AI Marketing Tools in 2026

    Best AI Marketing Tools in 2026

    Trying to pick the best AI marketing tool? An AI marketing tool 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 marketing tool 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 →
  • Talkman

    Talkman

    Talkman is an edutainment video game developed and published by Sony Computer Entertainment for the PlayStation Portable. It utilizes voice-activated translation software that operates in four languages, Japanese, English, Korean, and Mandarin Chinese. The name "Talkman" is a reference to Sony's Walkman line of portable audio products. It was released in Japan on November 17, 2005, and in America on August 5, 2008 (via the PlayStation Store), as Talkman Travel. In America, however, instead of receiving all the languages included in the Japanese version in one package, single-language packs are available for $2.99 each. Available packs are: Paris (French), Rome (Italian), and Tokyo (Japanese). The software is designed for travelers and entertainment, mostly containing slang and useful travel phrases. While originally sold in and designed for the Japanese market for Japanese users, its translation function operates between all four languages. In Japan, the software has proven popular with the middle-aged female demographic due to an interest in South Korean products, and Korean-language soap operas and movies; and as a fun English education aid for children. Outside of pure translations, Talkman also lets players play games to test their fluency of a language. The program comes with a USB microphone included. This microphone draws power through two gold-colored contacts on the top of the PSP, one on each side of the mini-USB port. This is uncommon due to the ability for most USB products to draw power through USB. These proprietary contacts are similar to the gold-colored contacts on the bottom-right of the device, which are used for charging. Note: The Chotto Shot (aka "Go!Cam") has a built-in microphone that also can be used with the Talkman program. Furthermore, the PSP-3000 model and PSP Go have built-in microphones that work with this application, without the need for any external attachments. == Talkman Euro == Following the success of the Asian version of Talkman, a version designed for translating European languages was developed and released on June 16, 2006. Talkman Euro is available in two versions. The Japanese version contains support for English, Italian, Spanish, German, French, and Japanese, while the Chinese version contains support for Traditional Chinese instead of Japanese. The differences on the packaging (the Japanese flag as opposed to a flag with the word "mie" in Chinese) are minimal and hard to notice. == Talkman UMD-only package == Talkman is also released as a UMD-only package, so users who already have the USB mic or camera can choose to purchase this standalone version. The Sony PSP Headset and the built-in microphone on later model PSPs have also been confirmed to work with Talkman.

    Read more →
  • F-score

    F-score

    In statistical analysis of binary classification and information retrieval systems, the F-score or F-measure is a measure of predictive performance. It is calculated from the precision and recall of the test, where the precision is the number of true positive results divided by the number of all samples predicted to be positive, including those not identified correctly, and the recall is the number of true positive results divided by the number of all samples that should have been identified as positive. Precision is also known as positive predictive value, and recall is also known as sensitivity in diagnostic binary classification. The F1 score is the harmonic mean of the precision and recall. It thus symmetrically represents both precision and recall in one metric. The more generic F β {\displaystyle F_{\beta }} score applies additional weights, valuing one of precision or recall more than the other. The highest possible value of an F-score is 1.0, indicating perfect precision and recall, and the lowest possible value is 0, if the precision or the recall is zero. == Etymology == The name F-measure is believed to be named after a different F function in Van Rijsbergen's book, when introduced to the Fourth Message Understanding Conference (MUC-4, 1992). == Definition == The traditional F-measure or balanced F-score (F1 score) is the harmonic mean of precision and recall: F 1 = 2 r e c a l l − 1 + p r e c i s i o n − 1 = 2 p r e c i s i o n ⋅ r e c a l l p r e c i s i o n + r e c a l l = 2 T P 2 T P + F P + F N {\displaystyle F_{1}={\frac {2}{\mathrm {recall} ^{-1}+\mathrm {precision} ^{-1}}}=2{\frac {\mathrm {precision} \cdot \mathrm {recall} }{\mathrm {precision} +\mathrm {recall} }}={\frac {2\mathrm {TP} }{2\mathrm {TP} +\mathrm {FP} +\mathrm {FN} }}} With precision = TP / (TP + FP) and recall = TP / (TP + FN), it follows that the numerator of F1 is the sum of their numerators and the denominator of F1 is the sum of their denominators. If FP=FN F 1 = 2 T P 2 T P + 2 F P = T P T P + F P {\displaystyle F_{1}={\frac {2\mathrm {TP} }{2\mathrm {TP} +2\mathrm {FP} }}={\frac {\mathrm {TP} }{\mathrm {TP} +\mathrm {FP} }}} or F 1 = 2 T P 2 T P + 2 F N = T P T P + F N {\displaystyle F_{1}={\frac {2\mathrm {TP} }{2\mathrm {TP} +2\mathrm {FN} }}={\frac {\mathrm {TP} }{\mathrm {TP} +\mathrm {FN} }}} So, F1 = precision = recall If TP=FP=FN F 1 = 2 T P 2 T P + 2 F P = 2 T P 4 T P = 1 2 = 0.5 {\displaystyle F_{1}={\frac {2\mathrm {TP} }{2\mathrm {TP} +2\mathrm {FP} }}={\frac {2\mathrm {TP} }{4\mathrm {TP} }}={\frac {1}{2}}=0.5} or F 1 = 2 T P 2 T P + 2 F N = 2 T P 4 T P = 1 2 = 0.5 {\displaystyle F_{1}={\frac {2\mathrm {TP} }{2\mathrm {TP} +2\mathrm {FN} }}={\frac {2\mathrm {TP} }{4\mathrm {TP} }}={\frac {1}{2}}=0.5} To see it as a harmonic mean, note that F 1 − 1 = 1 2 ( r e c a l l − 1 + p r e c i s i o n − 1 ) {\displaystyle F_{1}^{-1}={\frac {1}{2}}(\mathrm {recall} ^{-1}+\mathrm {precision} ^{-1})} . === Fβ score === A more general F score, F β {\displaystyle F_{\beta }} , that uses a positive real factor β {\displaystyle \beta } , where β {\displaystyle \beta } is chosen such that recall is considered β {\displaystyle \beta } times as important as precision, is: F β = β 2 + 1 ( β 2 ⋅ r e c a l l − 1 ) + p r e c i s i o n − 1 = ( 1 + β 2 ) ⋅ p r e c i s i o n ⋅ r e c a l l ( β 2 ⋅ p r e c i s i o n ) + r e c a l l {\displaystyle F_{\beta }={\frac {\beta ^{2}+1}{(\beta ^{2}\cdot \mathrm {recall} ^{-1})+\mathrm {precision} ^{-1}}}={\frac {(1+\beta ^{2})\cdot \mathrm {precision} \cdot \mathrm {recall} }{(\beta ^{2}\cdot \mathrm {precision} )+\mathrm {recall} }}} To see that as a weighted harmonic mean, note that F β − 1 = 1 β + β − 1 ( β ⋅ r e c a l l − 1 + β − 1 ⋅ p r e c i s i o n − 1 ) {\displaystyle F_{\beta }^{-1}={\frac {1}{\beta +\beta ^{-1}}}(\beta \cdot \mathrm {recall} ^{-1}+\beta ^{-1}\cdot \mathrm {precision} ^{-1})} . In terms of Type I and type II errors this becomes: F β = ( 1 + β 2 ) ⋅ T P ( 1 + β 2 ) ⋅ T P + β 2 ⋅ F N + F P = ( 1 + β 2 ) ⋅ T P ( T P + F N ) ⋅ β 2 + ( T P + F P ) {\displaystyle F_{\beta }={\frac {(1+\beta ^{2})\cdot \mathrm {TP} }{(1+\beta ^{2})\cdot \mathrm {TP} +\beta ^{2}\cdot \mathrm {FN} +\mathrm {FP} }}\,={\frac {(1+\beta ^{2})\cdot \mathrm {TP} }{(\mathrm {TP} +\mathrm {FN} )\cdot \beta ^{2}+(\mathrm {TP} +\mathrm {FP} )}}\,} Two commonly used values for β {\displaystyle \beta } are 2, which weighs recall higher than precision, and 1/2, which weighs recall lower than precision. The F-measure was derived so that F β {\displaystyle F_{\beta }} "measures the effectiveness of retrieval with respect to a user who attaches β {\displaystyle \beta } times as much importance to recall as precision". It is based on Van Rijsbergen's effectiveness measure E = 1 − ( α p + 1 − α r ) − 1 {\displaystyle E=1-\left({\frac {\alpha }{p}}+{\frac {1-\alpha }{r}}\right)^{-1}} Their relationship is: F β = 1 − E {\displaystyle F_{\beta }=1-E} where α = 1 1 + β 2 {\displaystyle \alpha ={\frac {1}{1+\beta ^{2}}}} == Diagnostic testing == This is related to the field of binary classification where recall is often termed "sensitivity". == Dependence of the F-score on class imbalance == Precision-recall curve, and thus the F β {\displaystyle F_{\beta }} score, explicitly depends on the ratio r {\displaystyle r} of positive to negative test cases. This means that comparison of the F-score across different problems with differing class ratios is problematic. One way to address this issue (see e.g., Siblini et al., 2020) is to use a standard class ratio r 0 {\displaystyle r_{0}} when making such comparisons. == Applications == The F-score is often used in the field of information retrieval for measuring search, document classification, and query classification performance. It is particularly relevant in applications which are primarily concerned with the positive class and where the positive class is rare relative to the negative class. Earlier works focused primarily on the F1 score, but with the proliferation of large scale search engines, performance goals changed to place more emphasis on either precision or recall and so F β {\displaystyle F_{\beta }} is seen in wide application. The F-score is also used in machine learning. However, the F-measures do not take true negatives into account, hence measures such as the Matthews correlation coefficient, Informedness or Cohen's kappa may be preferred to assess the performance of a binary classifier. The F-score has been widely used in the natural language processing literature, such as in the evaluation of named entity recognition and word segmentation. == Properties == The F1 score is the Dice coefficient of the set of retrieved items and the set of relevant items. The F1-score of a classifier which always predicts the positive class converges to 1 as the probability of the positive class increases. The F1-score of a classifier which always predicts the positive class is equal to 2 proportion_of_positive_class / ( 1 + proportion_of_positive_class ), since the recall is 1, and the precision is equal to the proportion of the positive class. If the scoring model is uninformative (cannot distinguish between the positive and negative class) then the optimal threshold is 0 so that the positive class is always predicted. F1 score is concave in the true positive rate. == Criticism == David Hand and others criticize the widespread use of the F1 score since it gives equal importance to precision and recall. In practice, different types of mis-classifications incur different costs. In other words, the relative importance of precision and recall is an aspect of the problem. According to Davide Chicco and Giuseppe Jurman, the F1 score is less truthful and informative than the Matthews correlation coefficient (MCC) in binary evaluation classification. David M W Powers has pointed out that F1 ignores the True Negatives and thus is misleading for unbalanced classes, while kappa and correlation measures are symmetric and assess both directions of predictability - the classifier predicting the true class and the true class predicting the classifier prediction, proposing separate multiclass measures Informedness and Markedness for the two directions, noting that their geometric mean is correlation. Another source of critique of F1 is its lack of symmetry. It means it may change its value when dataset labeling is changed - the "positive" samples are named "negative" and vice versa. This criticism is met by the P4 metric definition, which is sometimes indicated as a symmetrical extension of F1. Finally, Ferrer and Dyrland et al. argue that the expected cost (or its counterpart, the expected utility) is the only principled metric for evaluation of classification decisions, having various advantages over the F-score and the MCC. Both works show that the F-score can result in wrong conclusions about the absolute and relative quality of systems. == Difference from Fowlkes–Mallows index == While the F-measur

    Read more →
  • Keka HR

    Keka HR

    Keka HR is a software company that provides cloud-based human resource management and payroll automation software. Keka HR specializes in providing business services in the field of HR technology, payroll automation, recruiting, leave, attendance and performance management. The company was founded by Vijay Yalamanchili on July 21, 2014. The company is headquartered in Hyderabad, with operations in Singapore and the United States. == History == Keka HR was established in 2014 in Hyderabad, Telangana, India. In 2015, the company entered the Indian HR market and received the HYSEA Startup Award. By 2019, Keka HR had surpassed $1 million in annual recurring revenue (ARR). During the COVID-19 pandemic in 2020, the company reported a sevenfold increase in sales. By 2021, the company had raised $1.6 million through Recur Club. In 2022, Keka HR secured $57 million in Series A funding from West Bridge Capital. The company's headquarters are located in Gachibowli, Hyderabad, with offices in Singapore and Seattle, Washington.

    Read more →
  • Oren Etzioni

    Oren Etzioni

    Oren Etzioni (born 1964) is Professor Emeritus of Computer Science at the University of Washington, and founding CEO of the Allen Institute for Artificial Intelligence (AI2). Etzioni is a co-founder of Vercept, an AI startup, and founder and CEO of TrueMedia.org, a non-profit dedicated to fighting political deepfakes, which launched in April 2024. He is also the Founder and Technical Director of the AI2 Incubator and a venture partner at the Madrona Venture Group. == Early life and education == Etzioni is the son of Israeli-American intellectual Amitai Etzioni. He was the first student to major in computer science at Harvard University, where he earned a bachelor's degree in 1986. He earned a PhD from Carnegie Mellon University in January, 1991, supervised by Tom M. Mitchell. == University of Washington career == Etzioni joined the University of Washington faculty in 1991, immediately after receiving his PhD. He rose through the ranks to become the Washington Research Foundation Entrepreneurship Professor in Computer Science & Engineering. Etzioni's research has been focused on basic problems in the study of intelligence, machine reading, machine learning and web search. Past projects include Internet Softbots—the study of intelligent agents in the context of real-world software testbeds. In 2003, he started the KnowItAll project for acquiring massive amounts of information from the web. In 2005, he founded and became the director of the university's Turing Center. The center investigated problems in data mining, natural language processing, the Semantic Web and other web search topics. Etzioni coined the term machine reading and helped to create the first commercial comparison shopping agent. He has published over 200 technical papers, and his H-index exceeds 100. == Entrepreneurship == As a faculty member Etzioni was also an active entrepreneur, founding multiple companies and pioneering multiple technologies including MetaCrawler (bought by Infospace), Netbot (bought by Excite in 1997 for $35 million), and ClearForest (bought by Reuters). He founded Farecast, a travel metasearch and price prediction site, which was acquired by Microsoft in 2008 for $115 million. Before founding Farecast, he developed a program originally called Hamlet, that used algorithms to identify patterns in airfare data using data-mining techniques. He also co-founded Decide.com, a website to help consumers make buying decisions using previous price history and recommendations from other users. Decide.com was bought by eBay in September, 2013. Etzioni is also a venture partner at the Madrona Venture Group. He is founder and CEO of TrueMedia.org, a non-profit dedicated to fighting political deepfakes, which launched in April 2024. Etzioni is a co-founder of Vercept, an AI startup formed in 2025. == Founding CEO of AI2 == In September 2013 Etzioni was selected as the Founding CEO of the Allen Institute for Artificial Intelligence by philanthropist Paul G. Allen, and in January 2014 he took a leave of absence from the University of Washington to serve in that role. Etzioni's technical contributions continued at AI2; for example, in 2015, he helped to create the Semantic Scholar search engine. Under Etzioni’s leadership, AI2 grew from zero to over two hundred team members including notable researchers and engineers across several domains of AI. By 2021, its AI2 researchers had published near 700 papers in publications such as AAAI, ACL, CVPR, NeurIPS, and ICLR. Twenty-four of these papers had garnered special-recognition awards. AI2 also offered several key resources and tools to the AI community including the AllenNLP library, Semantic Scholar, and the conservation platforms EarthRanger and Skylight. Ed Lazowska, AI2 Board Member, has stated about Etzioni that he "took the collegial, collaborative culture that he absorbed in his 20+ years as a professor in UW's Allen School and mixed it with the singular focus that drives startups to create an elixir that AI2 folks have been drinking over the last eight years. The result is an exceptional organization of scientists, engineers, and entrepreneurs that's pursuing Paul Allen’s vision of ‘AI for the Common Good’ with extraordinary success.” == Popular press == In addition to his scientific publications, Etzioni has written commentary on AI for The New York Times, Wired, Nature, and other publications. After reading the idea in a book about AI by Brad Smith and Harry Shum, Etzioni has attempted to create an oath for AI practitioners. In 2018, he published what he called a "Hippocratic Oath for artificial intelligence practitioners" in TechCrunch. == Awards and recognition == In 1993, Etzioni received a National Young Investigator Award. In 2003, Etzioni was elected as AAAI Fellow. In 2005, Etzioni received an IJCAI Distinguished Paper Award for "A Probabilistic Model of Redundancy in Information Extraction". In 2007, he received the Robert S. Engelmore Memorial Award. In 2012 Etzioni was featured as GeekWire's "Geek of the Week". In 2013 Etzioni was voted "Geek of the Year" through GeekWire. In 2022, Etzioni received the 2012 ACL Test-of-Time Paper Award. In 2022, Etzioni, along with Ana-Maria Popescu and Henry Kautz, received the ACM Intelligent User Interfaces Most Impact Award for their 2003 paper, "Towards a Theory of Natural Language Interfaces to Databases". == Personal life == Etzioni has three children, and has said in interviews that family is his number one priority. He is married to Ivone Etzioni, and was previously married to Dr. Ruth Etzioni, a biostatistician at the Fred Hutchinson Cancer Center. Outside of his professional career, Etzioni has a wide range of personal interests. He has attended the Burning Man festival, which he described as a valuable way to step outside his comfort zone. His first computer was a TRS-80, and he has described his car’s GPS as his favorite gadget, joking that he has “no sense of direction.” == Selected publications == === Scholarly publications === Etzioni, Oren (July 1994). "A Softbot-based Interface to the Internet" (PDF). Communications of the ACM. Retrieved March 29, 2018. Etzioni, Oren (December 2008). "Open Information Extraction from the Web" (PDF). Communications of the ACM. Retrieved March 29, 2018. Zamir, Oren; Etzioni, Oren (1998). "Web document clustering". Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. ACM. pp. 46–54. doi:10.1145/290941.290956. ISBN 978-1-58113-015-7. S2CID 244069. Zamir, Oren; Etzioni, Oren (May 1999). "Grouper: a dynamic clustering interface to Web search results". Computer Networks. 31 (11–16): 1361–1374. CiteSeerX 10.1.1.31.8216. doi:10.1016/S1389-1286(99)00054-7. S2CID 206134308. Popescu, Ana-Maria; Etzioni, Oren (2005). "Extracting product features and opinions from reviews". Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05. pp. 339–346. doi:10.3115/1220575.1220618. Etzioni, Oren; Cafarella, Michael; Downey, Doug; Popescu, Ana-Maria; Shaked, Tal; Sonderland, Stephen; Weld, Daniel; Yates, Alexander (June 2005). "Unsupervised named-entity extraction from the Web: An experimental study". Artificial Intelligence. 165 (1): 91–134. doi:10.1016/j.artint.2005.03.001. Downey, Doug; Etzioni, Oren; Sonderland, Stephen (July 2010). "Grouper: Analysis of a probabilistic model of redundancy in unsupervised information extraction". Artificial Intelligence. 174 (11): 726–748. CiteSeerX 10.1.1.174.2441. doi:10.1016/j.artint.2010.04.024. === Popular articles === Etzioni, Oren (August 4, 2011). "Web Search Needs a Shakeup" (PDF). Nature. Retrieved November 21, 2019. Etzioni, Oren (December 9, 2014). "AI Won't Exterminate Us – It Will Empower Us". Backchannel. Retrieved March 29, 2018. Etzioni, Oren (February 4, 2016). "To Keep AI Safe -- Use AI". Vox. Retrieved November 21, 2019. Etzioni, Oren (April 8, 2016). "Quora Session with Oren Etzioni". Quora. Retrieved March 29, 2018. Etzioni, Oren (June 15, 2016). "Deep Learning Isn't a Dangerous Magic Genie. It's Just Math". Wired. Retrieved March 29, 2018. Etzioni, Oren (September 20, 2016). "No, the Experts Don't Think Superintelligent AI is a Threat to Humanity". MIT Technology Review. Retrieved November 21, 2019. Etzioni, Oren (July 6, 2017). "Artificial intelligence: AI Zooms in on highly influential citations". Nature. Retrieved March 29, 2018. Etzioni, Oren (September 1, 2017). "How to Regulate Artificial Intelligence". The New York Times. Retrieved March 29, 2018. Etzioni, Oren (November 2, 2017). "Workers Displaced by Automation Should Try A New Job: Caregiver". Wired. Retrieved March 29, 2018. Etzioni, Oren (March 14, 2018). "A Hippocratic Oath for artificial intelligence practitioners". Tech Crunch. Retrieved March 29, 2018. Etzioni, Oren (March 7, 2018). "A 'Manhattan Project' for science research". The Hill. Retrieved November 21, 2019. Etzioni, Ore

    Read more →
  • Michael Kohlhase

    Michael Kohlhase

    Michael Kohlhase (born 13 September 1964, in Erlangen) is a German computer scientist and professor at University of Erlangen–Nuremberg, where he is head of the KWARC research group (Knowledge Adaptation and Reasoning for Content). == Academic Positions == Michael Kohlhase is president of the OpenMath Society and a trustee of the Interest Group for Mathematical Knowledge Management (MKM). He was a trustee of the Conference on Automated Deduction and the CALCULEMUS Interest Group. He has been Conference Chair of CADE-21 and Program Chair of the KI-2006, MKM-2005, and CALCULEMUS-2000 conferences and has served on the Programme Committees of more than three dozen international conferences. Kohlhase holds an adjunct associate professorship at Carnegie Mellon University and was (2006–2008) vice director of the Department of Safe and Secure Cognitive Systems at German Research Centre for Artificial Intelligence (DFKI) Lab Bremen. In 2014, he became a member of the Global Digital Mathematics Library Working Group of the IMU. == Academic career == Michael Kohlhase obtained a degree in Mathematics (1989) from University of Bonn, a doctorate (1994) and habilitation (1999) in Computer Science at Saarland University. He has pursued his doctoral and post-doctoral research in extended research visits at Carnegie Mellon University, University of Amsterdam, the University of Edinburgh, and SRI International. From 2000–2003, he has conducted research and taught at the School of Computer Science at Carnegie Mellon University, where he was appointed to an adjunct associate professor. In September 2003 he was appointed as Professor of Computer Science at Jacobs University Bremen (International University Bremen until 2007), and 2006–2008 he was vice director of the Department of Safe and Secure Cognitive Systems of the German Research Centre for Artificial Intelligence (DFKI) Bremen. Since September 2016 he holds the Professorship for Knowledge Representation and Processing at University of Erlangen–Nuremberg. He has authored or edited four books and published almost 100 peer-reviewed papers. == Awards and Scholarships == 2000 3-year Heisenberg-Stipend of the Deutsche Forschungsgemeinschaft (DFG). 1996 AKI-prize, dissertation prize of the "Arbeitsgemeinschaft deutscher KI-Institute (AKI)" 1991 dissertation stipend of the Studienstiftung (German National Academic Foundation) 1986 masters stipend of Studienstiftung == Research interests == Michael Kohlhase's current research interests include Automated theorem proving and knowledge representation for mathematics, inference-based techniques for natural language processing and semantics, and computer-supported education. Much of his concrete work is based on web-based content markup formats like MathML, OpenMath, and OMDoc and systems for managing this data, e.g. semantic search engines for mathematical formulae, semantic extensions to LaTeX, or converting legacy LaTeX documents from the arXiv.

    Read more →
  • Stephen Wolfram

    Stephen Wolfram

    Stephen Wolfram ( WUUL-frəm; born 29 August 1959) is a British-American computer scientist, physicist, and businessman. He is known for his work in computer algebra and theoretical physics. In 2012, he was named a fellow of the American Mathematical Society. As a businessman, Wolfram is the founder and CEO of the software company Wolfram Research, where he works as chief designer of Mathematica and the Wolfram Alpha answer engine. == Early life == === Family === Stephen Wolfram was born in London in 1959 to Hugo and Sybil Wolfram, both German Jewish refugees to the United Kingdom. His maternal grandmother was British psychoanalyst Kate Friedlander. Wolfram's father, Hugo Wolfram, was a textile manufacturer and served as managing director of the Lurex Company—makers of the fabric Lurex. Wolfram's mother, Sybil Wolfram, was a Fellow and Tutor in Philosophy at Lady Margaret Hall at University of Oxford from 1964 to 1993. Wolfram is married to a mathematician. They have four children together. === Education === Wolfram was educated at Eton College, but left prematurely in 1976. As a young child, Wolfram had difficulties learning arithmetic. He entered St. John's College, Oxford, at age 17 and left in 1978 without graduating to attend the California Institute of Technology the following year, where he received a PhD in particle physics in 1980. Wolfram's thesis committee was composed of Richard Feynman, Peter Goldreich, Frank J. Sciulli, and Steven Frautschi, and chaired by Richard D. Field. == Early career == Wolfram, at the age of 15, began research in applied quantum field theory and particle physics and published scientific papers in peer-reviewed scientific journals; by the time he left Oxford, he had published ten such papers. Following his PhD, Wolfram joined the faculty at Caltech and became the youngest recipient of a MacArthur Fellowship in 1981, at age 21. == Later career == === Complex systems and cellular automata === In 1983, Wolfram left for the School of Natural Sciences of the Institute for Advanced Study in Princeton. By that time, he was no longer interested in particle physics. Instead, he began pursuing investigations into cellular automata, mainly with computer simulations. He produced a series of papers investigating the class of elementary cellular automata, conceiving the Wolfram code, a naming system for one-dimensional cellular automata, and a classification scheme for the complexity of their behaviour. He conjectured that the Rule 110 cellular automaton might be Turing complete, which a research assistant to Wolfram, Matthew Cook, later proved correct. Wolfram sued Cook and temporarily blocked publication of the work on Rule 110 for allegedly violating a non-disclosure agreement until Wolfram could publish the work in his controversial book A New Kind of Science. Wolfram's cellular-automata work came to be cited in more than 10,000 papers. In the mid-1980s, Wolfram worked on simulations of physical processes (such as turbulent fluid flow) with cellular automata on the Connection Machine alongside Richard Feynman and helped initiate the field of complex systems. In 1984, he was a participant in the Founding Workshops of the Santa Fe Institute, along with Nobel laureates Murray Gell-Mann, Manfred Eigen, and Philip Warren Anderson, and future laureate Frank Wilczek. In 1986, he founded the Center for Complex Systems Research (CCSR) at the University of Illinois Urbana–Champaign. In 1987, he founded the journal Complex Systems. === Symbolic Manipulation Program === Wolfram led the development of the computer algebra system SMP (Symbolic Manipulation Program) in the Caltech physics department during 1979–1981. A dispute with the administration over the intellectual property rights regarding SMP—patents, copyright, and faculty involvement in commercial ventures—eventually led him to resign from Caltech. SMP was further developed and marketed commercially by Inference Corp. of Los Angeles during 1983–1988. === Mathematica === In 1986, Wolfram left the Institute for Advanced Study for the University of Illinois Urbana–Champaign, where he had founded their Center for Complex Systems Research, and started to develop the computer algebra system Mathematica, which was released on 23 June 1988, when he left academia. In 1987, he founded Wolfram Research, which continues to develop and market the program. === A New Kind of Science === From 1992 to 2002, Wolfram worked on his controversial book A New Kind of Science, which presents an empirical study of simple computational systems. Additionally, it argues that for fundamental reasons these types of systems, rather than traditional mathematics, are needed to model and understand complexity in nature. Wolfram's conclusion is that the universe is discrete in its nature, and runs on fundamental laws that can be described as simple programs. He predicts that a realization of this within scientific communities will have a revolutionary influence on physics, chemistry, biology, and most other scientific areas, hence the book's title. The book was met with skepticism and criticism that Wolfram took credit for the work of others and made conclusions without evidence to support them. === Wolfram Alpha computational knowledge engine === In March 2009, Wolfram announced Wolfram Alpha, an answer engine. Wolfram Alpha launched in May 2009, and a paid-for version with extra features launched in February 2012 that was met with criticism for its high price, which later dropped from $50 to $2. The engine is based on natural language processing and a large library of rules-based algorithms. The application programming interface allows other applications to extend and enhance Wolfram Alpha. === Touchpress === In 2010, Wolfram co-founded Touchpress with Theodore Gray, Max Whitby, and John Cromie. The company specialised in creating in-depth premium apps and games covering a wide range of educational subjects designed for children, parents, students, and educators. Touchpress published more than 100 apps. The company is no longer active. === Wolfram Language === In March 2014, at the annual South by Southwest (SXSW) event, Wolfram officially announced the Wolfram Language as a new general multi-paradigm programming language, though it was previously available through Mathematica and not an entirely new programming language. The documentation for the language was pre-released in October 2013 to coincide with the bundling of Mathematica and the Wolfram Language on every Raspberry Pi computer with some controversy because of the proprietary nature of the Wolfram Language. While the Wolfram Language has existed for over 30 years as the primary programming language used in Mathematica, it was not officially named until 2014, and is not widely used. === Wolfram Physics Project === In April 2020, Wolfram announced the "Wolfram Physics Project" as an effort to reduce and explain all the laws of physics within a paradigm of a hypergraph that is transformed by minimal rewriting rules that obey the Church–Rosser property. The effort is a continuation of the ideas he originally described in A New Kind of Science. Wolfram claims that "From an extremely simple model, we're able to reproduce special relativity, general relativity and the core results of quantum mechanics." Physicists are generally unimpressed with Wolfram's claim, and say his results are non-quantitative and arbitrary. == Personal interests and activities == Wolfram has a log of personal analytics, including emails received and sent, keystrokes made, meetings and events attended, recordings of phone calls, and even physical movement dating back to the 1980s. In the preface of A New Kind of Science, he noted that he recorded over 100 million keystrokes and 100 mouse miles. He has said that personal analytics "can give us a whole new dimension to experiencing our lives." Wolfram was a scientific consultant for the 2016 film Arrival. He and his son Christopher Wolfram wrote some of the code featured on screen, such as the code in graphics depicting an analysis of the alien logograms, for which they used the Wolfram Language.

    Read more →
  • Vector database

    Vector database

    A vector database, vector store or vector search engine is a database that stores and retrieves embeddings of data in vector space. Vector databases typically implement approximate nearest neighbor algorithms so users can search for records semantically similar to a given input, unlike traditional databases which primarily look up records by exact match. Use-cases for vector databases include similarity search, semantic search, multi-modal search, recommendations engines, object detection, and retrieval-augmented generation (RAG). Vector embeddings are mathematical representations of data in a high-dimensional space. In this space, each dimension corresponds to a feature of the data, with the number of dimensions ranging from a few hundred to tens of thousands, depending on the complexity of the data being represented. Each data item is represented by one vector in this space. Words, phrases, or entire documents, as well as images, audio, and other types of data, can all be vectorized. These feature vectors may be computed from the raw data using machine learning methods such as feature extraction algorithms, word embeddings or deep learning networks. The goal is that semantically similar data items receive feature vectors close to each other. Vector retrieval can be combined with metadata filtering or lexical search to support filtered and hybrid retrieval workflows. == Techniques == Common techniques for similarity search on high-dimensional vectors include: Hierarchical Navigable Small World (HNSW) graphs Locality-sensitive hashing (LSH) and sketching Product quantization (PQ) Inverted files These techniques may also be combined in vector search systems. In recent benchmarks, HNSW-based implementations have been among the best performers. Conferences such as the International Conference on Similarity Search and Applications (SISAP) and the Conference on Neural Information Processing Systems (NeurIPS) have hosted competitions on vector search in large databases. == Applications == Vector databases are used in a wide range of machine learning applications including similarity search, semantic search, multi-modal search, recommendations engines, object detection, and retrieval-augmented generation. === Retrieval-augmented generation === An especially common use-case for vector databases is in retrieval-augmented generation (RAG), a method to improve domain-specific responses of large language models. The retrieval component of a RAG can be any search system, but is most often implemented as a vector database. Text documents describing the domain of interest are collected, and for each document or document section, a feature vector (known as an "embedding") is computed, typically using a deep learning network, and stored in a vector database along with a link to the document. Given a user prompt, the feature vector of the prompt is computed, and the database is queried to retrieve the most relevant documents. These are then automatically added into the context window of the large language model, and the large language model proceeds to create a response to the prompt given this context. == Implementations ==

    Read more →
  • Top 10 AI Video Generators Compared (2026)

    Top 10 AI Video Generators Compared (2026)

    Shopping for the best AI video generator? An AI video generator is software that uses machine learning to help you get more done — it keeps getting smarter as the underlying models improve. Pricing, accuracy, and the size of the model behind the tool are the three factors that most affect daily usefulness. Whether you are a beginner or a pro, the right AI video generator slots into your workflow and pays for itself fast. We tested the leading options and ranked them by quality, value, and ease of use.

    Read more →
  • General Internet Corpus of Russian

    General Internet Corpus of Russian

    General Internet Corpus of Russian (GICR) is a corpus of Russian internet texts that has been accessible on request through an online query interface since 2013. The corpus includes rich text materials from the blogosphere, social networks, major news sources and literary magazines. == Goals of the project == The project has the status of an educational and scientific one, and many tasks of computational linguistics are solved by independent researchers and research groups with the materials obtained by GICR. While other corpus projects of Russian are focused on fiction and edited texts, General Internet Corpus provides linguists timely opportunity to learn the language as it is, with all the slang and regional peculiarities. Corpus gives the opportunity to carry out research in Linguistic research of a wide range: dialectological research, study of word distribution, study of the language of the social networks, study of the influence of gender, age and other factors on the language, frequency of words, fixed expressions and different constructions, stylistic features of texts of different segments of the Internet, etc. Social media analysis Corpus-based machine learning for evaluating automatic tagging At various times, student papers and independent researches were carried out on the project material by students, graduates and employees of MSU, MIPT, Russian State Humanitarian University, Novosibirsk State University, Higher School of Economics, Russian Academy of Sciences, SFU, CSU, SGMP, IAAS of MSU. Scientific project leaders: Belikov V. - RSUH, Moscow, Russia Selegey V. - RSUH, ABBYY, Moscow, Russia Sharoff S. - RSUH, Moscow, Russia; University of Leeds, UK The organizations involved in support of GICR: Russian State University of Humanities ABBYY Company Moscow Institute of Physics and Technology Skolkovo Institute of Science and Technology == Size and content of the corpus == Corpus size for the summer 2016 is 19.8 billion tokens, of which 49% are from VKontakte, 40% are from LiveJournal, another 4% - from Mail.ru Blogs and News, and 2% - from Russian Magazine Hall. The sources collected in news segment are: RIA Novosti, Regnum, Lenta.ru, Rosbalt. Texts are provided with metamarkup (by date of creation of the text, sex, place and year of birth of the author, Internet genre, etc.); all texts are provided with automatic morphological tagging and lemmatization. Most of the texts collected are of 2013–2014 years of creation, although in some segments, such as in Russian Magazine Hall, there are some texts collected since 1994. GICR is one of the few mega-corpora projects nowadays, which means its available size is reaching several billion of words. == Access == Currently the interface of GICR is in beta stage, so access to the search in the corpora is provided and is free, but is available for researchers on request.

    Read more →