An Analysis on the Performance of Silicon Implementations of Backpropagation Algorithms for Artificial Neural Networks

Authors:
Leonardo M. Reyneri;Enrica Filippi
Affiliations:
-;-
Venue:
IEEE Transactions on Computers - Special issue on artificial neural networks
Year:
1991

Citing 6
Cited 5

Neural computing: theory and practice

Neural computing: theory and practice
Analog VLSI and neural systems

Analog VLSI and neural systems
VLSI Architectures for Neural Networks

IEEE Micro
An Analog VLSI Implementation of Hopfield's Neural Network

IEEE Micro
Simulation Machine and Integrated Implementation of Neural Networks: a Review of Methods, Problems and Realizations

Proceedings of the EURASIP Workshop 1990 on Neural Networks
Acceleration Techniques for the Backpropagation Algorithm

Proceedings of the EURASIP Workshop 1990 on Neural Networks

A Circuit Architecture for Analog On-Chip Back Propagation Learning with Local Learning Rate Adaptation

Analog Integrated Circuits and Signal Processing - Special issue on Learning on Silicon
Analog VLSI hardware implementation of a supervised learning algorithm

Hardware implementation of intelligent systems
Analog VLSI Implementation of Artificial Neural Networks with Supervised On-Chip Learning

Analog Integrated Circuits and Signal Processing
On the capabilities of neural networks using limited precision weights

Neural Networks
Design and Codesign of Neuro-Fuzzy Hardware

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The effects of silicon implementation on the backpropagation learning rule in artificial neural systems are examined. The effects on learning performance of limited weight resolution, range limitations, and the steepness of the activation function are considered. A minimum resolution of about 20/22 bits is generally required, but this figure can be reduced to about 14/15 bits by properly choosing the learning parameter eta which attains good performance in presence of limited resolution. This performance can be further improved by using a modified batch backpropagation rule. Theoretical analysis is compared with ad-hoc simulations and results are discussed in detail.