A digital hardware pulse-mode neuron with piecewise linear activation function

Authors:
H. Hikawa
Affiliations:
Dept. of Comput. Sci. & Intelligent Syst., Oita Univ., Japan
Venue:
IEEE Transactions on Neural Networks
Year:
2003

Citing 0
Cited 7

MATLAB Simulink modeling and simulation of LVI-based primal-dual neural network for solving linear and quadratic programs

Neurocomputing
Hardware Neural Network for a Visual Inspection System

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Self-adjusting ring modules (SARMs) for flexible gait pattern generation

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Improved Zhang neural network model and its solution of time-varying generalized linear matrix equations

Expert Systems with Applications: An International Journal
Artificial neural networks in hardware: A survey of two decades of progress

Neurocomputing
FPGA implementation of a wavelet neural network with particle swarm optimization learning

Mathematical and Computer Modelling: An International Journal
Hardware implementation of new bell-shaped pulse mode neural network with on-chip learning and application to image processing

International Journal of High Performance Systems Architecture

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new type of digital pulse-mode neuron that employs piecewise-linear function as its activation function. The neuron is implemented on field programmable gate array (FPGA) and tested by experiments. As well as theoretical analysis, the experimental results show that the piecewise-linear function of the proposed neuron is programmable and robust against the change in the number of input signals. To demonstrate the effect of piecewise-linear activation function, pulse-mode multilayer neural network with on-chip learning is implemented on FPGA with the proposed neuron, and its learning performance is verified by experiments. By approximating the sigmoid function by the piecewise-linear function, the convergence rate of the learning and generalization capability are improved.