Artificial Neural Networks: Concept LearningJoachim Diederich Learning is one of the most important features of artificial neural networks (ANN). This volume is a representative overview of the most important ANN learning techniques. The topics covered include connectionist learning procedures, dynamic connections in neural networks, connectionist recruitment |
Contents
Connectionist Learning Procedures | 2 |
Dynamic Connections in Neural Networks | 45 |
Connectionist Recruitment Learning | 63 |
Copyright | |
7 other sections not shown
Other editions - View all
Common terms and phrases
actions activity adaptive elements architecture Artificial Neural Networks associative memory assume attribute space backpropagation Barto behavior Boltzmann machine bottom-up boxes system cart-pole clamped coarticulation committed units competitive learning components concept unit connectionist learning constraints desired output deterministic distribution dynamic connection dynamic link Edited encode environment error propagation expected reinforcement F₁ F₂ feedback feedforward Feldman Figure free units function global gradient gradient descent Hebbian learning hidden units Hinton Hopfield Hopfield nets IEEE implemented input patterns input units input vector input-output intermediate units ISBN layer learning algorithm learning procedure linear Neural Networks neurons nodes output units output vectors parallel Parallel Distributed Processing parameter pathway perceptron performance phonemes prediction probability problem recognition reinforcement learning reinforcement signal represent representation Rumelhart sequence simulations stable stochastic structure subnetwork supervised learning supraliminally task theory tion top-down expectation training example update variables weight change