Текст книги "Глоссариум по искусственному интеллекту: 2500 терминов. Том 2"

Co-adaptation is when neurons predict patterns in training data by relying almost exclusively on outputs of specific other neurons instead of relying on the network’s behavior as a whole. When the patterns that cause co-adaption are not present in validation data, then co-adaptation causes overfitting. Dropout regularization reduces co-adaptation because dropout ensures neurons cannot rely solely on specific other neurons220220
  Co-adaptation [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#co-adaptation (дата обращения: 03.05.2023)


[Закрыть].

COBWEB is an incremental system for hierarchical conceptual clustering. COBWEB was invented by Professor Douglas H. Fisher, currently at Vanderbilt University. COBWEB incrementally organizes observations into a classification tree. Each node in a classification tree represents a class (concept) and is labeled by a probabilistic concept that summarizes the attribute-value distributions of objects classified under the node. This classification tree can be used to predict missing attributes or the class of a new object221221
  COBWEB [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Cobweb_(clustering) (дата обращения: 10.05.2023)


[Закрыть].

Code is a one-to-one mapping of a finite ordered set of symbols belonging to some finite alphabet222222
  Код [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Код (дата обращения: 03.05.2023)


[Закрыть].

Codec is a codec is the means by which sound and video files are compressed for storage and transmission purposes. There are various forms of compression: ’lossy’ and ’lossless’, but most codecs perform lossless compression because of the much larger data reduction ratios that occur with lossy compression. Most codecs are software, although in some areas codecs are hardware components of image and sound systems. Codecs are necessary for playback, since they uncompress or decompress the moving image and sound files and allow them to be rendered223223
  Codec [Электронный ресурс] www.umich.edu URL: https://www.icpsr.umich.edu/web/ICPSR/cms/2042#C (дата обращения: 07.07.2022)


[Закрыть].

Cognitive architecture – the Institute of Creative Technologies defines cognitive architecture as: «hypothesis about the fixed structures that provide a mind, whether in natural or artificial systems, and how they work together – in conjunction with knowledge and skills embodied within the architecture – to yield intelligent behavior in a diversity of complex environments»224224
  Cognitive architecture [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Cognitive_architecture (дата обращения: 03.05.2023)


[Закрыть].

Cognitive computing is used to refer to the systems that simulate the human brain to help with the decision– making. It uses self-learning algorithms that perform tasks such as natural language processing, image analysis, reasoning, and human—computer interaction. Examples of cognitive systems are IBM’s Watson and Google DeepMind225225
  Cognitive computing [Электронный ресурс] https://habr.com URL: https://habr.com/ru/company/ibm/blog/276855/ (дата обращения: 31.01.2022)


[Закрыть].

Cognitive Maps are structured representations of decision depicted in graphical format (variations of cognitive maps are cause maps, influence diagrams, or belief nets). Basic cognitive maps include nodes connected by arcs, where the nodes represent constructs (or states) and the arcs represent relationships. Cognitive maps have been used to understand decision situations, to analyze complex cause-effect representations and to support communication226226
  Cognitive Maps [Электронный ресурс] www.igi-global.com URL: https://www.igi-global.com/dictionary/qplan/34624 (дата обращения: 07.07.2022)


[Закрыть].

Cognitive science – the interdisciplinary scientific study of the mind and its processes227227
  Cognitive science Когнитивная наука и интеллектуальные технологии: Реф. сб. АН СССР. – М.: Ин-т науч. информ. по обществ. наукам, 1991 (дата обращения: 04.02.2022)


[Закрыть].

Cohort is a sample in study (conducted to evaluate a machine learning algorithm, for example) where it is followed prospectively or retrospectively and subsequent status evaluations with respect to a disease or outcome are conducted to determine which initial participants’ exposure characteristics (risk factors) are associated with it.

Cold-Start is a potential issue arising from the fact that a system cannot infer anything for users or items for which it has not gathered a sufficient amount of information yet228228
  Cold-Start [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Cold_start_(recommender_systems) (дата обращения 07.07.2023)


[Закрыть].

Collaborative filtering – making predictions about the interests of one user based on the interests of many other users. Collaborative filtering is often used in recommendation systems229229
  Collaborative filtering [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#collaborative-filtering (дата обращения: 03.05.2023)


[Закрыть].

Combinatorial optimization in operations research, applied mathematics and theoretical computer science, combinatorial optimization is a topic that consists of finding an optimal object from a finite set of objects230230
  Combinatorial optimization [Электронный ресурс] https://dic.academic.ru URL: https://dic.academic.ru/dic.nsf/ruwiki/107404 (дата обращения: 11.02.2022)


[Закрыть].

Committee machine is a type of artificial neural network using a divide and conquer strategy in which the responses of multiple neural networks (experts) are combined into a single response. The combined response of the committee machine is supposed to be superior to those of its constituent experts. Compare ensembles of classifiers231231
  Committee machine [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Committee_machine (дата обращения: 03.05.2023)


[Закрыть].

Commoditization is the process of transforming a product from an elite to a generally available (comparatively cheap commodity of mass consumption)232232
  Коммодитизация [Электронный ресурс] https://secretmag.ru URL: https://secretmag.ru/enciklopediya/chto-takoe-kommoditizaciya-obyasnyaem-prostymi-slovami.htm (дата обращения: 07.07.2022)


[Закрыть].

Common Data Element (CDE) is a tool to support data management for clinical research233233
  Common Data Element (CDE) [Электронный ресурс] https://techdocs.broadcom.com URL: https://techdocs.broadcom.com/us/en/ca-mainframe-software/traditional-management/ca-mics-resource-management/14-1/installing/system-modification/ca-mics-facilities/ca-mics-component-generator-mcg/generator-definition-statements/common-data-element-definition-statements.html (дата обращения 30.04.2022)


[Закрыть].

Commonsense reasoning is a branch of artificial intelligence concerned with simulating the human ability to make presumptions about the type and essence of ordinary situations they encounter every day234234
  Commonsense reasoning [Электронный ресурс] https://sciencedirect.com URL: https://www.sciencedirect.com/topics/computer-science/ answer-set-programming#:~:text=Answer%20set%20programming %20is%20an, is%20required%20in%20commonsense%20reasoning (дата обращения: 09.03.2022)


[Закрыть].

Compiler is a program that translates text written in a programming language into a set of machine codes. AI framework compilers collect the computational data of the frameworks and try to optimize the code of each of them, regardless of the hardware of the accelerator. The compiler contains programs and blocks with which the framework performs several tasks. The computer memory resource allocator, for example, allocates power individually for each accelerator235235
  Компилятор [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Компилятор (дата обращения: 03.05.2023)


[Закрыть].

Composite AI is a combined application of various artificial intelligence methods (deep machine learning, computer vision, natural language processing, contextual analysis, knowledge graphs, data visualization, forecasting methods, etc.) to increase the efficiency of model training in order to achieve a synergistic effect from their use and the best results of the work of artificial intelligence systems. One of the ideas that is laid down in the creation of composite artificial intelligence is to obtain a sane artificial intelligence that will be able to understand the essence of the problems and solve a wide range of problems, offering optimal solutions.236236
  Composite AI [Электронный ресурс] https://www.expert.ai URL: https://www.expert.ai/glossary-of-ai-terms/ (дата обращения: 04.05.2023)


[Закрыть],237237
  .Сергей Стельмах. Почему композитный ИИ – критически важная концепция. [Электронный ресурс] www.itweek.ru URL: https://www.itweek.ru/ai/article/detail.php?ID=219809 (дата обращения: 31.08.2023). – Текст: электронный.


[Закрыть],238238
  .Композитный ИИ: что это такое и зачем он нужен? [Электронный ресурс] sas.cnews.ru URL: https://sas.cnews.ru/articles/2021-06-30_kompozitnyj_ii_novyj_hajp_ili_novye (дата обращения: 31.08.2023). – Текст: электронный.


[Закрыть].

Compression is a method of reducing the size of computer files. There are several compression programs available, such as gzip and WinZip239239
  Compression [Электронный ресурс] www.umich.edu URL: https://www.icpsr.umich.edu/web/ICPSR/cms/2042#C (дата обращения: 07.07.2022)


[Закрыть].

Computation is any type of arithmetic or non-arithmetic calculation that follows a well-defined model (e.g., an algorithm)240240
  Computation [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computation (дата обращения: 07.07.2022)


[Закрыть].

Computational chemistry is a discipline using mathematical methods for the calculation of molecular properties or for the simulation of molecular behaviour. It also includes, e.g., synthesis planning, database searching, combinatorial library manipulation.241241
  Computational chemistry [Электронный ресурс] https://goldbook.iupac.org URL: https://goldbook.iupac.org/terms/view/CT06952 (дата обращения: 28.03.2023)


[Закрыть],242242
  Computational chemistry [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_chemistry (дата обращения: 28.03.2023)


[Закрыть],243243
  Вычислительная химия [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Вычислительная_химия (дата обращения: 28.03.2023)


[Закрыть].

Computational complexity theory – focuses on classifying computational problems according to their inherent difficulty, and relating these classes to each other. A computational problem is a task solved by a computer. A computation problem is solvable by mechanical application of mathematical steps, such as an algorithm244244
  Computational complexity theory [Электронный ресурс] https://math-cs.spbu.ru URL: https://math-cs.spbu.ru/courses/teoriya-slozhnosti-vychislenij/ (дата обращения: 09.02.2022)


[Закрыть].

Computational creativity (also artificial creativity, mechanical creativity, creative computing, or creative computation) is a multidisciplinary endeavour that includes the fields of artificial intelligence, cognitive psychology, philosophy, and the arts245245
  Computational creativity [Электронный ресурс] https://hoster.bmstu.ru URL: http://hoster.bmstu.ru/~amas/cources/mv/lect__slides.pdf (дата обращения: 14.02.2022)


[Закрыть].

Computational cybernetics is the integration of cybernetics and computational intelligence techniques246246
  Computational cybernetics [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_cybernetics (дата обращения: 28.03.2023)


[Закрыть].

Computational efficiency of an agent or a trained model is the amount of computational resources required by the agent to solve a problem at the inference stage247247
  Вычислительная эффективность агента или обученной модели [Электронный ресурс] https://vc.ru URL: https://vc.ru/ml/253499-kak-schitat-effektivnost-iskusstvennogo-intellekta-na-primere-umnogo-ekskavatora (дата обращения: 28.03.2023)


[Закрыть].

Computational efficiency of an intelligent system is the amount of computing resources required to train an intelligent system with a certain level of performance on a given volume of tasks248248
  Вычислительная эффективность интеллектуальной системы [Электронный ресурс] https://vc.ru URL: https://vc.ru/ml/253499-kak-schitat-effektivnost-iskusstvennogo-intellekta-na-primere-umnogo-ekskavatora (дата обращения: 28.03.2023)


[Закрыть].

Computational Graphics Processing Unit (computational GPU, cGPU) – graphic processor-computer, GPU-computer, multi-core GPU used in hybrid supercomputers to perform parallel mathematical calculations; for example, one of the first GPUs in this category contains more than 3 billion transistors – 512 CUDA cores and up to 6 GB of memory249249
  Computational Graphics Processing Unit [Электронный ресурс] www.boston.co.uk URL: https://www.boston.co.uk/info/nvidia-kepler/what-is-gpu-computing.aspx (дата обращения 14.03.2022)


[Закрыть].

Computational humor is a branch of computational linguistics and artificial intelligence which uses computers in humor research250250
  Computational humor [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_humor (дата обращения: 28.03.2023)


[Закрыть].

Computational intelligence (CI) usually refers to the ability of a computer to learn a specific task from data or experimental observation251251
  Computational intelligence [Электронный ресурс] www.semanticscholar.org URL: https://www.semanticscholar.org/topic/Computational-intelligence/4778 (дата обращения 28.02.2022)


[Закрыть].

Computational learning theory (COLT) in computer science, is a subfield of artificial intelligence devoted to studying the design and analysis of machine learning algorithms252252
  Computational learning theory (COLT) [Электронный ресурс] www.semanticscholar.org URL: https://www.semanticscholar.org/topic/Computational-learning-theory/164025 (дата обращения 28.02.2022)


[Закрыть].

Computational linguistics is an interdisciplinary field concerned with the statistical or rule-based modeling of natural language from a computational perspective, as well as the study of appropriate computational approaches to linguistic questions253253
  Computational linguistics [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_linguistics (дата обращения: 04.05.2023)


[Закрыть].

Computational mathematics is the mathematical research in areas of science where computing plays an essential role254254
  Вычислительная математика [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/ (дата обращения: 28.03.2023)


[Закрыть].

Computational neuroscience (also known as theoretical neuroscience or mathematical neuroscience) is a branch of neuroscience which employs mathematical models, theoretical analysis and abstractions of the brain to understand the principles that govern the development, structure, physiology, and cognitive abilities of the nervous system255255
  Computational neuroscience [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_neuroscience (дата обращения: 28.03.2023)


[Закрыть],256256
  Вычислительная нейробиология [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Вычислительная_нейробиология (дата обращения: 28.03.2023)


[Закрыть].

Computational number theory (also algorithmic number theory) – the study of algorithms for performing number theoretic computations257257
  Computational number theory [Электронный ресурс] https://en-academic.com URL: https://en-academic.com/dic.nsf/enwiki/282959 (дата обращения: 28.03.2023)


[Закрыть],,258258
  Вычислительная теория чисел [Электронный ресурс] https://wiki5.ru URL: https://wiki5.ru/wiki/Computational_number_theory (дата обращения: 28.03.2023)


[Закрыть].

Computational problem in theoretical computer science is a mathematical object representing a collection of questions that computers might be able to solve259259
  Computational problem [Электронный ресурс] https://cs.stackexchange.com URL: https://cs.stackexchange.com/questions/47757/computational-problem-definition (дата обращения 12.03.2022)


[Закрыть].

Computational statistics (or statistical computing) is the application of computer science and software engineering principles to solving scientific problems. It involves the use of computing hardware, networking, algorithms, programming, databases and other domain-specific knowledge to design simulations of physical phenomena to run on computers. Computational science crosses disciplines and can even involve the humanities260260
  Computational statistics [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computational_statistics (дата обращения: 28.03.2023)


[Закрыть],261261
  Computational statistics (Computational science) [Электронный ресурс] https://www.techopedia.com URL: https://www.techopedia.com/definition/6579/computational-science (дата обращения: 28.03.2023)


[Закрыть].

Computer engineering — technologies for digital modeling and design of objects and production processes throughout the life cycle262262
  Компьютерный инжиниринг [Электронный ресурс] http://fingramota.by URL: http://fingramota.by/ru/services/library/dictionary/1/К (дата обращения: 04.05.2023)


[Закрыть].

Computer incident is a fact of violation and (or) cessation of the operation of a critical information infrastructure object, a telecommunication network used to organize the interaction of such objects, and (or) a violation of the security of information processed by such an object, including as a result of a computer attack263263
  Компьютерный инцидент [Электронный ресурс] http://government.ru URL: http://government.ru/docs/all/112572/ ФЗ №187 от 26.07.2017 «О безопасности критической информационной инфраструктуры РФ» (дата обращения: 04.05.2023)


[Закрыть].

Computer science – the theory, experimentation, and engineering that form the basis for the design and use of computers. It involves the study of algorithms that process, store, and communicate digital information. A computer scientist specializes in the theory of computation and the design of computational systems. Computer science is the study of computation, automation, and information. Computer science spans theoretical disciplines (such as algorithms, theory of computation, and information theory) to practical disciplines (including the design and implementation of hardware and software). Computer science is generally considered an area of academic research and distinct from computer programming264264
  Computer science [Электронный ресурс] https://view.officeapps.live.com URL: %2Fsrc%2FZibtceva4.do https://view.officeapps.live.com/op/view.aspx?src=http%3A%2F%2Fwww.lib.unn.ru%2Fstudentsc&wdOrigin=BROWSELINK (дата обращения: 07.07.2022)


[Закрыть].

Computer simulation is the process of mathematical modelling, performed on a computer, which is designed to predict the behaviour of, or the outcome of, a real-world or physical system. The reliability of some mathematical models can be determined by comparing their results to the real-world outcomes they aim to predict. Computer simulations have become a useful tool for the mathematical modeling of many natural systems in physics (computational physics), astrophysics, climatology, chemistry, biology and manufacturing, as well as human systems in economics, psychology, social science, health care and engineering265265
  Computer simulation [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computer_simulation (дата обращения: 07.07.2022)


[Закрыть].

Computer vision (CV) is scientific discipline, field of technology and the direction of artificial intelligence (AI), which deals with computer processing, recognition, analysis and classification of dynamic images of reality. It is widely used in video surveillance systems, in robotics and in modern industry to improve product quality and production efficiency, comply with legal requirements, etc. In computer vision, the following areas are distinguished: face recognition (face recognition), image recognition (image recognition), augmented reality (augmented reality (AR) and optical character recognition (OCR). Synonyms – artificial vision, machine vision266266
  Computer vision [Электронный ресурс] https://www.clickworker.com URL: https://www.clickworker.com/ai-glossary/computer-vision/ (дата обращения: 04.05.2023)


[Закрыть].

Computer vision processing (CVP) is the processing of images (signals) in a computer vision system, in computer vision systems – about algorithms (computer vision processing algorithms), processors (computer vision processing unit, CVPU), convolutional neural networks (convolutional neural network), which are used for image processing and implementation of visual functions in robotics, real-time systems, smart video surveillance systems, etc.267267
  Обработка компьютерного зрения [Электронный ресурс] https://books.google.ru URL: https://books.google.ru/books?id=Computer vision processing стр. 102 Англо-русский толковый словарь по искусственному интеллекту и робототехнике (дата обращения: 11.05.2023)


[Закрыть].

Computer-Aided Detection/Diagnosis (CAD), uses computer programs to assist radiologists in the interpretation of medical images. CAD systems process digital images for typical appearances and highlight suspicious regions in order to support a decision taken by a professional268268
  Computer-Aided Detection/Diagnosis (CAD) [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computer-aided_diagnosis (дата обращения: 04.05.2023)


[Закрыть].

Computer-automated design (CAutoD) – design automation usually refers to electronic design automation, or Design Automation which is a Product Configurator. Extending Computer-Aided Design (CAD), automated design and computer-automated designare concerned with a broader range of applications, such as automotive engineering, civil engineering, composite material design, control engineering, dynamic system identification and optimization, financial systems, industrial equipment, mechatronic systems, steel construction, structural optimisation, and the invention of novel systems. More recently, traditional CAD simulation is seen to be transformed to CAutoD by biologically inspired machine learning, including heuristic search techniques such as evolutionary computation, and swarm intelligence algorithms269269
  Computer-automated design [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Computer-automated_design (дата обращения: 04.05.2023)


[Закрыть].

Computing modules are plug-in specialized computers designed to solve narrowly focused tasks, such as accelerating the work of artificial neural networks algorithms, computer vision, voice recognition, machine learning and other artificial intelligence methods, built on the basis of a neural processor – a specialized class of microprocessors and coprocessors (processor, memory, data transfer).

Computing system is a software and hardware complex intended for solving problems and processing data (including calculations) or several interconnected complexes that form a single infrastructure270270
  Вычислительная система [Электронный ресурс] https://ru.wikipedia.org URL: https://cdto.wiki/Вычислительная_система (дата обращения: 28.03.2023)


[Закрыть].

Computing units are blocks that work like a filter that transforms packets according to certain rules. The instruction set of the calculator can be limited, which guarantees a simple internal structure and a sufficiently high speed of operation271271
  Вычислительные блоки [Электронный ресурс] https://www.osp.ru URL: https://www.osp.ru/os/1997/06/179341 (дата обращения: 28.03.2023)


[Закрыть].

Сoncept drift in predictive analytics and machine learning, the concept drift means that the statistical properties of the target variable, which the model is trying to predict, change over time in unforeseen ways. This causes problems because the predictions become less accurate as time passes272272
  Сoncept drift [Электронный ресурс] https://deepchecks.com URL: https://deepchecks.com/how-to-detect-concept-drift-with-machine-learning-monitoring/ (дата обращения 12.03.2022)


[Закрыть].

Сonnectionism is an approach in the fields of cognitive science, that hopes to explain mental phenomena using artificial neural networks273273
  Сonnectionism [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Connectionism (дата обращения: 04.05.2023)


[Закрыть],274274
  Коннекционизм [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Коннекционизм (дата обращения: 04.05.2023)


[Закрыть].

Сonsistent heuristic in the study of path-finding problems in artificial intelligence, a heuristic function is said to be consistent, or monotone, if its estimate is always less than or equal to the estimated distance from any neighboring vertex to the goal, plus the cost of reaching that neighbor275275
  Сonsistent heuristic [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Consistent_heuristic (дата обращения: 26.06.2023)


[Закрыть].

Сonstrained conditional model (CCM) is a machine learning and inference framework that augments the learning of conditional (probabilistic or discriminative) models with declarative сonstraints276276
  Constrained conditional model [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Constrained_conditional_model (дата обращения: 07.07.2022)


[Закрыть].

Constraint logic programming is a form of constraint programming, in which logic programming is extended to include concepts from constraint satisfaction. A constraint logic program is a logic program that contains constraints in the body of clauses277277
  Сonstraint logic programming [Электронный ресурс] www.definitions.net URL: https://www.definitions.net/definition/Constraint (дата обращения 28.02.2022)


[Закрыть].

Constraint programming is a programming paradigm wherein relations between variables are stated in the form of constraints. Constraints differ from the common primitives of imperative programming languages in that they do not specify a step or sequence of steps to execute, but rather the properties of a solution to be found278278
  Сonstraint programming [Электронный ресурс] www.definitions.net URL: https://www.definitions.net/definition/Constraint (дата обращения 28.02.2022)


[Закрыть].

Constructed language (also conlang) is a language whose phonology, grammar, and vocabulary are consciously devised, instead of having developed naturally. Constructed languages may also be referred to as artificial, planned, or invented languages279279
  Искусственные языки [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Портал:Искусственные_языки (дата обращения: 02.05.2023)


[Закрыть].

Control theory in control systems engineering, is a subfield of mathematics that deals with the control of continuously operating dynamical systems in engineered processes and machines. The objective is to develop a control model for controlling such systems using a control action in an optimum manner without delay or overshoot and ensuring control stability280280
  Сontrol theory [Электронный ресурс] www.semanticscholar.org URL: https://www.semanticscholar.org/paper/Modern-control-systems-theory-Leondes-青木/c0fb8d86dec3dc0d09c207fa9888369328b766a9 (дата обращения 06.04.2022)


[Закрыть].

Convolutional neural network (CNN, or ConvNet) in deep learning, is a class of deep neural networks, most commonly applied to analyzing visual imagery. CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics. Сonvolutional neural network is a class of artificial neural network most commonly used to analyze visual images. They are also known as Invariant or Spatial Invariant Artificial Neural Networks (SIANN) based on an architecture with a common weight of convolution kernels or filters that slide over input features and provide equivalent translation responses known as feature maps281281
  Сonvolutional neural network (CNN, or ConvNet) [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Convolutional_neural_network (дата обращения: 30.06.2023)


[Закрыть].

Confidentiality of information is a mandatory requirement for a person who has access to certain information not to transfer such information to third parties without the consent of its owner282282
  Конфиденциальность информации [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Конфиденциальность (дата обращения: 04.05.2023)


[Закрыть].

Confirmation Bias – the tendency to search for, interpret, favor, and recall information in a way that confirms one’s own beliefs or hypotheses while giving disproportionately less attention to information that contradicts it283283
  Предвзятость подтверждения [Электронный ресурс] https://te-st.ru URL: https://te-st.ru/2019/11/29/why-is-artificial-intelligence-biased/ (дата обращения: 04.02.2022)


[Закрыть].

Confusion matrix is a situational analysis table that summarizes the prediction results of a classification model in machine learning. The records in the dataset are summarized in a matrix according to the real category and the classification score made by the classification model284284
  Confusion matrix [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Confusion_matrix (дата обращения: 10.05.2023)


[Закрыть],285285
  Confusion matrix [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#confusion-matrix (дата обращения: 10.05.2023)


[Закрыть].

Consumer artificial intelligence is specialized artificial intelligence programs embedded in consumer devices and processes286286
  Бытовой искусственный интеллект [Электронный ресурс] https://apr.moscow URL: https://apr.moscow/content/data/6/11 Технологии искусственного интеллекта. pdf (дата обращения: 28.03.2023)


[Закрыть].

Continuous feature is a floating-point feature with an infinite range of possible values. Contrast with discrete feature287287
  Continuous feature [Электронный ресурс] https://www.primeclasses.in URL: https://www.primeclasses.in/glossary/data-science-course/machine-learning/continuous-feature (дата обращения: 11.05.2023)


[Закрыть],288288
  Непрерывная функция [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Непрерывная_функция (дата обращения: 11.05.2023)


[Закрыть].

Contributor is a human worker providing annotations on the Appen data annotation platform289289
  Contributor [Электронный ресурс] https://bigdataanalyticsnews.com URL: https://bigdataanalyticsnews.com/artificial-intelligence-glossary/ (дата обращения: 02.07.2023)


[Закрыть].

Convenience sampling – using a dataset not gathered scientifically in order to run quick experiments. Later on, it’s essential to switch to a scientifically gathered dataset290290
  Convenience sampling [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convenience-sampling (дата обращения 04.07.2023)


[Закрыть].

Convergence – informally, often refers to a state reached during training in which training loss and validation loss change very little or not at all with each iteration after a certain number of iterations. In other words, a model reaches convergence when additional training on the current data will not improve the model. In deep learning, loss values sometimes stay constant or nearly so for many iterations before finally descending, temporarily producing a false sense of convergence. See also early stopping291291
  Convergence [Электронный ресурс] https://www.primeclasses.in URL: https://www.primeclasses.in/glossary/data-science-course/machine-learning/convergence (дата обращения: 04.05.2023)


[Закрыть],292292
  Convergence [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convergence (дата обращения: 04.05.2023)


[Закрыть].

Convex function is a function in which the region above the graph of the function is a convex set. The prototypical convex function is shaped something like the letter U. For example, the following are all convex functions:

By contrast, the following function is not convex. Notice how the region above the graph is not a convex set:

A strictly convex function has exactly one local minimum point, which is also the global minimum point. The classic U-shaped functions are strictly convex functions. However, some convex functions (for example, straight lines) are not U-shaped. A lot of the common loss functions, including the following, are convex functions: L2 loss; Log Loss; L1 regularization; L2 regularization. Many variations of gradient descent are guaranteed to find a point close to the minimum of a strictly convex function. Similarly, many variations of stochastic gradient descent have a high probability (though, not a guarantee) of finding a point close to the minimum of a strictly convex function. The sum of two convex functions (for example, L2 loss + L1 regularization) is a convex function. Deep models are never convex functions. Remarkably, algorithms designed for convex optimization tend to find reasonably good solutions on deep networks anyway, even though those solutions are not guaranteed to be a global minimum293293
  Convex function [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convex-function (дата обращения: 28.03.2023)


[Закрыть],294294
  Convex function [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#expandable-7 (дата обращения: 28.03.2023)


[Закрыть].

Convex optimization – the process of using mathematical techniques such as gradient descent to find the minimum of a convex function. A great deal of research in machine learning has focused on formulating various problems as convex optimization problems and in solving those problems more efficiently. For complete details, see Boyd and Vandenberghe, Convex Optimization295295
  Convex optimization [Электронный ресурс] https://en.mimi.hu URL: https://en.mimi.hu/artificial_intelligence/convex_optimization.html (дата обращения 22.02.2022)


[Закрыть].

Convex set is a subset of Euclidean space such that a line drawn between any two points in the subset remains completely within the subset.296296
  Convex set [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convex-set (дата обращения: 28.03.2023)


[Закрыть].

Convolution — the process of filtering. A filter (or equivalently: a kernel or a template) is shifted over an input image. The pixels of the output image are the summed product of the values in the filter pixels and the corresponding values in the underlying image297297
  Convolution [Электронный ресурс] https://spec-zone.ru/ URL: https://spec-zone.ru/RU/OSX/documentation/Performance/Conceptual/vImage/ConvolutionOperations/ConvolutionOperations.html (дата обращения: 09.02.2022)


[Закрыть].

Convolutional filter – one of the two actors in a convolutional operation. (The other actor is a slice of an input matrix). A convolutional filter is a matrix having the same rank as the input matrix, but a smaller shape298298
  Convolutional filter [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convolutional-filter (дата обращения: 30.06.2023)


[Закрыть].

Convolutional layer is a layer of a deep neural network in which a convolutional filter passes along an input matrix299299
  Convolutional layer [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convolutional-layer (дата обращения: 30.06.2023)


[Закрыть].

Convolutional neural network (CNN) is a type of neural network that identifies and interprets images300300
  Convolutional neural network (CNN) [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convolutional-neural-network (дата обращения: 29.06.2023)


[Закрыть],301301
  Convolutional neural network (CNN) [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Convolutional_neural_network (дата обращения: 29.06.2023)


[Закрыть].

Convolutional operation – the following two-step mathematical operation: Element-wise multiplication of the convolutional filter and a slice of an input matrix. (The slice of the input matrix has the same rank and size as the convolutional filter); Summation of all the values in the resulting product matrix302302
  Convolutional operation [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#convolutional-operation (дата обращения: 30.06.2023)


[Закрыть].

Corelet programming environment (CPE) is a scalable environment that allows programmers to set the functional behavior of a neural network by adjusting its parameters and communication characteristics303303
  Среда программирования Corelet (CPE) [Электронный ресурс] https://www.osp.ru URL: https://www.osp.ru/os/2019/03/13055127 (дата обращения: 02.07.2023)


[Закрыть].

Corpus of texts is a large dataset of written or spoken material that can be used to train a machine to perform linguistic tasks304304
  Корпус текстов [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Корпус_текстов (дата обращения: 04.05.2023)


[Закрыть].

Correlation analysis is a statistical data processing method that measures the strength of the relationship between two or more variables. Thus, it determines whether there is a connection between the phenomena and how strong the connection between these phenomena is305305
  Корреляционный анализ [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Корреляция#Корреляционный_анализ (дата обращения: 04.05.2023)


[Закрыть].

Correlation is a statistical relationship between two or more random variables306306
  Корреляция [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Корреляция (дата обращения: 04.05.2023)


[Закрыть].

Cost – synonym for loss. A measure of how far a model’s predictions are from its label. Or, to put it more pessimistically, a measure of how bad a model is. To determine this value, the model must define a loss function. For example, linear regression models typically use the standard error for the loss function, while logistic regression models use the log loss307307
  Cost [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#cost (дата обращения: 02.07.2023)


[Закрыть],308308
  Cost [Электронный ресурс] https://quizlet.com URL: https://quizlet.com/300254930/machine-learning-google-course-flash-cards/ (дата обращения: 02.07.2023)


[Закрыть].

Co-training essentially amplifies independent signals into a stronger signal. For instance, consider a classification model that categorizes individual used cars as either Good or Bad. One set of predictive features might focus on aggregate characteristics such as the year, make, and model of the car; another set of predictive features might focus on the previous owner’s driving record and the car’s maintenance history. The seminal paper on co-training is Combining Labeled and Unlabeled Data with Co-Training by Blum and Mitchell309309
  Co-training [Электронный ресурс] www.v7labs.com URL: https://www.v7labs.com/blog/semi-supervised-learning-guide (дата обращения 06.03.2022)


[Закрыть].

Counterfactual fairness is a fairness metric that checks whether a classifier produces the same result for one individual as it does for another individual who is identical to the first, except with respect to one or more sensitive attributes. Evaluating a classifier for counterfactual fairness is one method for surfacing potential sources of bias in a model. See «When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness» for a more detailed discussion of counterfactual fairness310310
  Counterfactual fairness [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#counterfactual-fairness (дата обращения: 04.05.2023)


[Закрыть].

Coverage bias – this bias means that the study sample is not representative and that the data set in the array has zero chance of being included in the sample311311
  Coverage bias [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#coverage-bias (дата обращения: 30.06.2023)


[Закрыть].

Crash blossom is a sentence or phrase with an ambiguous meaning. Crash blossoms present a significant problem in natural language understanding. For example, the headline Red Tape Holds Up Skyscraper is a crash blossom because an NLU model could interpret the headline literally or figuratively312312
  Crash blossom [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#crash-blossom (дата обращения: 09.04.2023)


[Закрыть].

Critic – synonym for Deep Q-Network313313
  Critic [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#critic (дата обращения: 04.05.2023)


[Закрыть].

Critical information infrastructure – objects of critical information infrastructure, as well as telecommunication networks used to organize the interaction of such objects314314
  Критическая информационная инфраструктура [Электронный ресурс] https://it-enigma.ru URL: https://it-enigma.ru/about/news/chto-takoe-kriticheskaya-informaczionnaya-infrastruktura-(kii)) (дата обращения: 12.07.2023)


[Закрыть].

Critical information infrastructure of the Russian Federation is a set of critical information infrastructure objects, as well as telecommunication networks used to organize the interaction of critical information infrastructure objects with each other315315
  Критическая информационная инфраструктура РФ [Электронный ресурс] http://government.ru URL: http://government.ru/docs/all/112572/ ФЗ №187 от 26.07.2017 «О безопасности критической информационной инфраструктуры РФ» (дата обращения: 04.05.2023)


[Закрыть].

Cross-entropy is a generalization of Log Loss to multi-class classification problems. Cross-entropy quantifies the difference between two probability distributions. See also perplexity316316
  Cross-entropy [Электронный ресурс] https://helenkapatsa.ru URL: https://www.helenkapatsa.ru/kross-entropiia/ (дата обращения: 16.02.2022)


[Закрыть].

Crossover (also recombination) in genetic algorithms and evolutionary computation, a genetic operator used to combine the genetic information of two parents to generate new offspring. It is one way to stochastically generate new solutions from an existing population, and analogous to the crossover that happens during sexual reproduction in biological organisms. Solutions can also be generated by cloning an existing solution, which is analogous to asexual reproduction. Newly generated solutions are typically mutated before being added to the population317317
  Crossover [Электронный ресурс] https://brainly.in URL: https://brainly.in/question/5802477 (дата обращения 28.02.2022)


[Закрыть].

Cross-Validation (k-fold Cross-Validation, Leave-p-out Cross-Validation) is a collection of processes designed to evaluate how the results of a predictive model will generalize to new data sets. k-fold Cross-Validation; Leave-p-out Cross-Validation318318
  Перекрёстная проверка [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Перекрёстная_проверка (дата обращения: 20.06.2023)


[Закрыть].

Cryogenic freezing (cryonics, human cryopreservation) is a technology of preserving in a state of deep cooling (using liquid nitrogen) the head or body of a person after his death with the intention to revive them in the future319319
  Криогенная заморозка [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Крионика (дата обращения: 04.05.2023)


[Закрыть].

Cyber-physical systems are intelligent networked systems with built-in sensors, processors and drives that are designed to interact with the physical environment and support the operation of computer information systems in real time320320
  Киберфизические системы [Электронный ресурс] https://ulgov.ru URL: https://ulgov.ru/page/index/permlink/id/14949/ (дата обращения: 02.05.2023)


[Закрыть].