Original Contribution: Training nets of hardware realizable sigma-pi units

Authors:
Kevin N. Gurney
Affiliations:
-
Venue:
Neural Networks
Year:
1992

Citing 2
Cited 9

On the approximate realization of continuous mappings by neural networks

Neural Networks
System identification-A survey

Automatica (Journal of IFAC)

Original Contribution: Training nets of stochastic units using system identification

Neural Networks
Transformations of sigma-pi nets: obtaining reflected functions by reflecting weight matrices

Neural Networks
Information processing in dendrites-I.: input pattern generalisation

Neural Networks
Training Product Unit Neural Networks with Genetic Algorithms

IEEE Expert: Intelligent Systems and Their Applications
Comparing a brain-inspired robot action selection mechanism with winner-takes-all

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Predicting the behaviour of G-RAM networks

Neural Networks
NEUROM: a ROM based RNS digital neuron

Neural Networks
Third-order generalization: A new approach to categorizing higher-order generalization

Neurocomputing
Convergence of BP algorithm for product unit neural networks with exponential weights

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Learning convergence is demonstrated for networks of nodes which are defined by a population of values at the vertices of the n-dimensional hypercube. These are functionally equivalent to higher order nodes or sigma-pi units but have the potential to be implemented in readily available memory components. The cube based structure also offers insight into the process of generalization. Three algorithms are discussed: reward-penalty, back propagation, and a new one based on system identification in control theory. It is shown that reward-penalty style techniques emerge as a special case of system identification.