Artificial neural networks (ANNs), usually simply called neural networks (NNs) or, more simply yet, neural nets, are computing systems inspired by the biological neural networks that constitute animal brains.
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the main benefit of searchability. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer science, linguistics and computer engineering fields. The reverse process is speech synthesis.
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.
In computer science, evolutionary computation is a family of algorithms for global optimization inspired by biological evolution, and the subfield of artificial intelligence and soft computing studying these algorithms. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character.
Algorithmic composition is the technique of using algorithms to create music.
A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed or undirected graph along a temporal sequence. This allows it to exhibit temporal dynamic behavior. Derived from feedforward neural networks, RNNs can use their internal state (memory) to process variable length sequences of inputs. This makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition. Recurrent neural networks are theoretically Turing complete and can run arbitrary programs to process arbitrary sequences of inputs.
In predictive analytics and machine learning, 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 passes.
Vasant G. Honavar is an Indian born American computer scientist, and artificial intelligence, machine learning, big data, data science, causal inference, knowledge representation, bioinformatics and health informatics researcher and professor.
A memetic algorithm (MA) in computer science and operations research, is an extension of the traditional genetic algorithm. It may provide a sufficiently good solution to an optimization problem. It uses a local search technique to reduce the likelihood of premature convergence.
An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. The connectivity and weights of hidden neurons are fixed and randomly assigned. The weights of output neurons can be learned so that the network can produce or reproduce specific temporal patterns. The main interest of this network is that although its behaviour is non-linear, the only weights that are modified during training are for the synapses that connect the hidden neurons to output neurons. Thus, the error function is quadratic with respect to the parameter vector and can be differentiated easily to a linear system.
James D. McCaffrey is a research software engineer at Microsoft Research known for his contributions to machine learning, combinatorics, and software test automation.
Computational creativity is a multidisciplinary endeavour that is located at the intersection of the fields of artificial intelligence, cognitive psychology, philosophy, and the arts.
Artificial intelligence and music (AIM) is a common subject in the International Computer Music Conference, the Computing Society Conference and the International Joint Conference on Artificial Intelligence. The first International Computer Music Conference (ICMC) was held in 1974 at Michigan State University. Current research includes the application of AI in music composition, performance, theory and digital sound processing.
Hit Song Science is a term coined by Mike McCready and trademarked by the company he co-founded, Polyphonic HMI. It concerns the possibility of predicting whether a song will be a hit, before its distribution using automated means such as machine learning software.
In computer science, an evolving intelligent system is a fuzzy logic system which improves the own performance by evolving rules. The technique is known from machine learning, in which external patterns are learned by an algorithm. Fuzzy logic based machine learning works with neuro-fuzzy systems.
Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.
Multi-task optimization is a paradigm in the optimization literature that focuses on solving multiple self-contained tasks simultaneously. The paradigm has been inspired by the well-established concepts of transfer learning and multi-task learning in predictive analytics.
Rita Cucchiara is an Italian electrical and computer engineer, and professor of computer architecture and computer vision in the Enzo Ferrari Department of Engineering at the University of Modena and Reggio Emilia (UNIMORE) in Italy. Cucchiara's work focuses on artificial intelligence, specifically deep network technologies and computer vision to human behavior understanding (HBU). She is the director of the AImage Lab at UNIMORE and is director of the Artificial Intelligence Research and Innovation Center (AIRI) as well as the ELLIS Unit at Modena. She was founder and director from 2018 to 2021 of the Italian National Lab of Artificial Intelligence and intelligent systems of CINI. Cucchiara was also president of the CVPL GIRPR the Italian Association of Computer Vision, Machine Learning and Pattern Recognition from 2016 to 2018.
Conformal prediction (CP) is a set of algorithms devised to assess the uncertainty of predictions produced by a machine learning model. CP algorithms do this by computing and comparing nonconformity measure, of examples from the training set, and compare these with measure computed for examples from a test set. Conformal predictors can be divided into inductive and transductive. These mainly differ in their computational complexity and whether they can be applied to regression or classification tasks. Inductive algorithms train one or several machine learning models which are re-used for future test objects, and can be used for both classification and regression tasks, whereas transductive algorithms re-train the model for every test object, and can only be used for classification tasks.
