Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Constructive higher-order network that is polynomial time
Neural Networks
Handbook of Neural Computation
Handbook of Neural Computation
On sequential construction of binary neural networks
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Two low complexity methods for neural network construction, that areapplicable to various neural network models, are introduced and evaluated forhigh order perceptrons. The methods are based on a Boolean approximation ofreal-valued data. This approximation is used to construct an initial neuralnetwork topology which is subsequently trained on the original (real-valued) data. The methods are evaluated for their effectiveness in reducing the network sizeand increasing the network‘s generalization capabilities in comparison tofully connected high order perceptrons.