Analogue Imprecision In Mlp Training, Progress In Neural Processing, Vol 4Hardware inaccuracy and imprecision are important considerations when implementing neural algorithms. This book presents a study of synaptic weight noise as a typical fault model for analogue VLSI realisations of MLP neural networks and examines the implications for learning and network performance. The aim of the book is to present a study of how including an imprecision model into a learning scheme as a“fault tolerance hint” can aid understanding of accuracy and precision requirements for a particular implementation. In addition the study shows how such a scheme can give rise to significant performance enhancement. |
Contents
Chapter 2 Neural Network Performance Metrics | |
Chapter 3 Noise in Neural Implementations | |
Chapter 4 Simulation Requirements and Environment | |
Chapter 5 Fault Tolerance | |
Chapter 6 Generalisation Ability | |
Chapter 7 Learning Trajectory and Speed | |
Other editions - View all
Common terms and phrases
accuracy accuracy and precision additive noise analogue hardware analogue imprecision analysis artificial neural networks assessment back-propagation capacity Chapter character encoder problem classification error com computation con considered cost function de-stabilising discussed distribution effect error surface eye/not-eye classifier fault model fault tolerance performance feed-forward forward pass generalisation ability generalisation performance gradient gradient descent Graph showing hardware implementations hardware model Henon map hidden layer implications improvements initial weight range input issues learning algorithm learning trajectory levels of noise levels of synaptic limitations localisation problem mathematical analysis mean square error method minimised multiplicative noise net networks trained neural algorithms neural network neurons noise level output parameters penalty terms perceptron performance enhancements performance metrics pre precision predictions prob random series prediction sigmoid curve sigmoid function simulated annealing simulation experiments stochastic synaptic noise synaptic weight noise test problems tion trained network training data trajectory and speed verify weight changes weight saliency