Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Stewart W. Wilson"'
More than sixty contributions in From Animals to Animats 2 by researchers in ethology, ecology, cybernetics, artificial intelligence, robotics, and related fields investigate behaviors and the underlying mechanisms that allow animals and, potentially
August 8-12, 1994, Brighton, England From Animals to Animats 3 brings together research intended to advance the front tier of an exciting new approach to understanding intelligence. The contributors represent a broad range of interests from artificia
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2620b55469c1b41a280ee6ae51449d87
http://arxiv.org/abs/1910.10579
http://arxiv.org/abs/1910.10579
Autor:
Stewart W. Wilson
Publikováno v:
ACM SIGEVOlution. 5:2-6
Stewart W. Wilson is certainly one of the most innovative and functionality-oriented thinkers I have ever had the honor to meet. His research career commenced at the Massachusetts Institute of Technology (MIT), where he received an S.B. degree in phy
Publikováno v:
IEEE Transactions on Evolutionary Computation. 12:355-376
An important strength of learning classifier systems (LCSs) lies in the combination of genetic optimization techniques with gradient-based approximation techniques. The chosen approximation technique develops locally optimal approximations, such as a
Autor:
Martin V. Butz, Stewart W. Wilson
Publikováno v:
Soft Computing - A Fusion of Foundations, Methodologies and Applications. 6:144-153
A concise description of the XCS classifier system's parameters, structures, and algorithms is presented as an aid to research. The algorithms are written in modularly structured pseudo code with accompanying explanations.
Publikováno v:
Information Processing Letters. 82:23-30
Rules are an accepted means of representing knowledge for virtually every domain. Traditional machine learning methods derive rules by exploring sets of examples using statistical or information theoretic techniques. Alternatively, rules can be disco
Autor:
Stewart W. Wilson
Publikováno v:
ACM SIGEVOlution. 2:20-22
Autor:
Stewart W. Wilson
Publikováno v:
Evolutionary Computation. 3:149-175
In many classifier systems, the classifier strength parameter serves as a predictor of future payoff and as the classifier's fitness for the genetic algorithm. We investigate a classifier system, XCS, in which each classifier maintains a prediction o
Autor:
Stewart W. Wilson
Publikováno v:
Evolutionary Computation. 2:1-18
A basic classifier system, ZCS, is presented that keeps much of Holland's original framework but simplifies it to increase understandability and performance. ZCS's relation to Q-learning is brought out, and their performances compared in environments