Unsupervised learning in general connectionist systems
1a Laboratório de Mecatrónica, Departamento de Engenharia Electrotécnica e de Computadores , Instituto Superior Técnico , Av. Rovisco Pais, 1096 Lisbon Codex, Portugal.
Abstract:
There is a common framework in which different connectionist systems may be treated in a unified way. The general system in which they may all be mapped is a network which, in addition to the connection strengths, has an adaptive node parameter controlling the output intensity. In this paper we generalize two neural network learning schemes to networks with node parameters. In generalized Hebbian learning we find improvements to the convergence rate for small eigenvalues in principal component analysis. For competitive learning the use of node parameters also seems useful in that, by emphasizing or de-emphasizing the dominance of winning neurons, either improved robustness or discrimination is obtained.
Related Concept Videos
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Second Order systems II
Associative Learning
Classical conditioning, also known...
Purposive Learning
Observational Learning
Learning Disabilities
Dyslexia
Dyslexia is a...


