Presentation	2002/11/4 Pulse mode neuron with piecewise linear activation function Hiroomi HIKAWA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	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 provided by the proposed neuron is programmable and robust. To demonstrate the effect of piecewise linear function, pulse mode multilayer neural network with on-chip learning is implemented on FPGA with the proposed neuron, and its feasibility is verified by experiments. By approximating the sigmoid function by the piecewise linear function, the convergence rate of the learning is improved.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	activation function / pulse neural network / on-chip learning / FPGA
Paper #	NC2002-76
Date of Issue

Conference Information
Committee	NC
Conference Date	2002/11/4(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Neurocomputing (NC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Pulse mode neuron with piecewise linear activation function
Sub Title (in English)
Keyword(1)	activation function
Keyword(2)	pulse neural network
Keyword(3)	on-chip learning
Keyword(4)	FPGA
1st Author's Name	Hiroomi HIKAWA
1st Author's Affiliation	Faculty of Engineering, Oita University()
Date	2002/11/4
Paper #	NC2002-76
Volume (vol)	vol.102
Number (no)	430
Page	pp.pp.-
#Pages	6
Date of Issue