Artificial neuron is a mathematical function conceived as a model of biological neurons, a neural network. The difference between an artificial neuron and a biological neuron is shown in the figure. Artificial neurons are the elementary units of an artificial neural network. An artificial neuron receives one or more inputs (representing excitatory postsynaptic potentials and inhibitory postsynaptic potentials on nerve dendrites) and sums them to produce an output signal (or activation, representing the action potential of the neuron that is transmitted down its axon). Typically, each input is weighted separately, and the sum is passed through a non-linear function known as an activation function or transfer function. Transfer functions are usually sigmoid, but they can also take the form of other non-linear functions, piecewise linear functions, or step functions. They are also often monotonically increasing, continuous, differentiable, and bounded93,94.
Artificial Superintelligence (ASI) is a term referring to the time when the capability of computers will surpass humans. «Artificial intelligence,» which has been much used since the 1970s, refers to the ability of computers to mimic human thought. Artificial superintelligence goes a step beyond and posits a world in which a computers cognitive ability is superior to a humans95.
Assistive intelligence is AI-based systems that help make decisions or perform actions.
Association for the Advancement of Artificial Intelligence (AAAI) is an international, nonprofit, scientific society devoted to promote research in, and responsible use of, artificial intelligence. AAAI also aims to increase public understanding of artificial intelligence (AI), improve the teaching and training of AI practitioners, and provide guidance for research planners and funders concerning the importance and potential of current AI developments and future directions96.
Association is another type of unsupervised learning method that uses different rules to find relationships between variables in a given dataset. These methods are frequently used for market basket analysis and recommendation engines, along the lines of «Customers Who Bought This Item Also Bought» recommendations97.
Association Rule Learning is a rule-based Machine Learning method for discovering interesting relations between variables in large data sets98.
Asymptotic computational complexity in computational complexity theory, asymptotic computational complexity is the usage of asymptotic analysis for the estimation of computational complexity of algorithms and computational problems, commonly associated with the usage of the big O notation99.
Asynchronous inter-chip protocols are protocols for data exchange in low-speed devices; instead of frames, individual characters are used to control the exchange of data100.
Attention mechanism is one of the key innovations in the field of neural machine translation. Attention allowed neural machine translation models to outperform classical machine translation systems based on phrase translation. The main bottleneck in sequence-to-sequence learning is that the entire content of the original sequence needs to be compressed into a vector of a fixed size. The attention mechanism facilitates this task by allowing the decoder to look back at the hidden states of the original sequence, which are then provided as a weighted average as additional input to the decoder101.
Attributional calculus (AC) is a logic and representation system defined by Ryszard S. Michalski. It combines elements of predicate logic, propositional calculus, and multi-valued logic. Attributional calculus provides a formal language for natural induction, an inductive learning process whose results are in forms natural to people102.
Augmented Intelligence is the intersection of machine learning and advanced applications, where clinical knowledge and medical data converge on a single platform. The potential benefits of Augmented Intelligence are realized when it is used in the context of workflows and systems that healthcare practitioners operate and interact with. Unlike Artificial Intelligence, which tries to replicate human intelligence, Augmented Intelligence works with and amplifies human intelligence103.
Augmented reality (AR) is an interactive experience of a real-world environment where the objects that reside in the real-world are «augmented» by computer-generated perceptual information, sometimes across multiple sensory modalities, including visual, auditory, haptic, somatosensory, and olfactory104.
Augmented reality technologies are visualization technologies based on adding information or visual effects to the physical world by overlaying graphic and/or sound content to improve user experience and interactive features105.
Auto Associative Memory is a single layer neural network in which the input training vector and the output target vectors are the same. The weights are determined so that the network stores a set of patterns. As shown in the following figure, the architecture of Auto Associative memory network has «n number of input training vectors and similar «n number of output target vectors106.
Autoencoder (AE) is a type of Artificial Neural Network used to produce efficient representations of data in an unsupervised and non-linear manner, typically to reduce dimensionality107.
Automata theory the study of abstract machines and automata, as well as the computational problems that can be solved using them. It is a theory in theoretical computer science and discrete mathematics (a subject of study in both mathematics and computer science). Automata theory (part of the theory of computation) is a theoretical branch of Computer Science and Mathematics, which mainly deals with the logic of computation with respect to simple machines, referred to as automata108,109.
Automated control system a set of software and hardware designed to control technological and (or) production equipment (executive devices) and the processes they produce, as well as to control such equipment and processes110.
Automated planning and scheduling (also simply AI planning) is a branch of artificial intelligence that concerns the realization of strategies or action sequences, typically for execution by intelligent agents, autonomous robots and unmanned vehicles. Unlike classical control and classification problems, the solutions are complex and must be discovered and optimized in multidimensional space. Planning is also related to decision theory111.
Automated processing of personal data processing of personal data using computer technology112.
Automated reasoning is an area of computer science and mathematical logic dedicated to understanding different aspects of reasoning. The study of automated reasoning helps produce computer programs that allow computers to reason completely, or nearly completely, automatically. Although automated reasoning is considered a sub-field of artificial intelligence, it also has connections with theoretical computer science, and even philosophy113.
Automated system is an organizational and technical system that guarantees the development of solutions based on the automation of information processes in various fields of activity114.
Automation bias is when a human decision maker favors recommendations made by an automated decision-making system over information made without automation, even when the automated decision-making system makes errors115.
Automation is a technology by which a process or procedure is performed with minimal human intervention116.
Autonomic computing is the ability of a system to adaptively self-manage its own resources for high-level computing functions without user input117.
Autonomous artificial intelligence is a biologically inspired system that tries to reproduce the structure of the brain, the principles of its operation with all the properties that follow from this118,119.
Autonomous car (also self-driving car, robot car, and driverless car) is a vehicle that is capable of sensing its environment and moving with little or no human input120.
Autonomous is a machine is described as autonomous if it can perform its task or tasks without needing human intervention121.
Autonomous robot is a robot that performs behaviors or tasks with a high degree of autonomy. Autonomous robotics is usually considered to be a subfield of artificial intelligence, robotics, and information engineering122.
Autonomous vehicle is a mode of transport based on an autonomous driving system. The control of an autonomous vehicle is fully automated and carried out without a driver using optical sensors, radar and computer algorithms123.
Autoregressive Model is an autoregressive model is a time series model that uses observations from previous time steps as input to a regression equation to predict the value at the next time step. In statistics and signal processing, an autoregressive model is a representation of a type of random process. It is used to describe certain time-varying processes in nature, economics, etc.124.
Auxiliary intelligence systems based on artificial intelligence that complement human decisions and are able to learn in the process of interacting with people and the environment.
Average precision is a metric for summarizing the performance of a ranked sequence of results. Average precision is calculated by taking the average of the precision values for each relevant result (each result in the ranked list where the recall increases relative to the previous result)125.
Ayasdi is an enterprise scale machine intelligence platform that delivers the automation that is needed to gain competitive advantage from the companys big and complex data. Ayasdi supports large numbers of business analysts, data scientists, endusers, developers and operational systems across the organization, simultaneously creating, validating, using and deploying sophisticated analyses and mathematical models at scale126.
«B»
Backpropagation through time (BPTT) is a gradient-based technique for training certain types of recurrent neural networks. It can be used to train Elman networks. The algorithm was independently derived by numerous researchers127.
Backpropagation, also called «backward propagation of errors,» is an approach that is commonly used in the training process of the deep neural network to reduce errors128.
Backward Chaining, also called goal-driven inference technique, is an inference approach that reasons backward from the goal to the conditions used to get the goal. Backward chaining inference is applied in many different fields, including game theory, automated theorem proving, and artificial intelligence129.
Bag-of-words model in computer vision. In computer vision, the bag-of-words model (BoW model) can be applied to image classification, by treating image features as words. In document classification, a bag of words is a sparse vector of occurrence counts of words; that is, a sparse histogram over the vocabulary. In computer vision, a bag of visual words is a vector of occurrence counts of a vocabulary of local image features130.
Bag-of-words model is a simplifying representation used in natural language processing and information retrieval (IR). In this model, a text (such as a sentence or a document) is represented as the bag (multiset) of its words, disregarding grammar and even word order but keeping multiplicity. The bag-of-words model has also been used for computer vision. The bag-of-words model is commonly used in methods of document classification where the (frequency of) occurrence of each word is used as a feature for training a classifier131.
Baldwin effect the skills acquired by organisms during their life as a result of learning, after a certain number of generations, are recorded in the genome132.
Baseline is a model used as a reference point for comparing how well another model (typically, a more complex one) is performing. For example, a logistic regression model might serve as a good baseline for a deep model. For a particular problem, the baseline helps model developers quantify the minimal expected performance that a new model must achieve for the new model to be useful133.
Batch the set of examples used in one gradient update of model training134.
Batch Normalization is a preprocessing step where the data are centered around zero, and often the standard deviation is set to unity135.
Batch size the number of examples in a batch. For example, the batch size of SGD is 1, while the batch size of a mini-batch is usually between 10 and 1000. Batch size is usually fixed during training and inference; however, TensorFlow does permit dynamic batch sizes136,137.
Bayess Theorem is a famous theorem used by statisticians to describe the probability of an event based on prior knowledge of conditions that might be related to an occurrence138.
Bayesian classifier in machine learning is a family of simple probabilistic classifiers based on the use of the Bayes theorem and the «naive» assumption of the independence of the features of the objects being classified139.
Bayesian Filter is a program using Bayesian logic. It is used to evaluate the header and content of email messages and determine whether or not it constitutes spam unsolicited email or the electronic equivalent of hard copy bulk mail or junk mail. A Bayesian filter works with probabilities of specific words appearing in the header or content of an email. Certain words indicate a high probability that the email is spam, such as Viagra and refinance140.
Bayesian Network, also called Bayes Network, belief network, or probabilistic directed acyclic graphical model, is a probabilistic graphical model (a statistical model) that represents a set of variables and their conditional dependencies via a directed acyclic graph141.
Bayesian optimization is a probabilistic regression model technique for optimizing computationally expensive objective functions by instead optimizing a surrogate that quantifies the uncertainty via a Bayesian learning technique. Since Bayesian optimization is itself very expensive, it is usually used to optimize expensive-to-evaluate tasks that have a small number of parameters, such as selecting hyperparameters142.
Bayesian programming is a formalism and a methodology for having a technique to specify probabilistic models and solve problems when less than the necessary information is available143,144.
Bees algorithm is a population-based search algorithm which was developed by Pham, Ghanbarzadeh and et al. in 2005. It mimics the food foraging behaviour of honey bee colonies. In its basic version the algorithm performs a kind of neighbourhood search combined with global search, and can be used for both combinatorial optimization and continuous optimization. The only condition for the application of the bees algorithm is that some measure of distance between the solutions is defined. The effectiveness and specific abilities of the bees algorithm have been proven in a number of studies145.