Title :
An efficient pulse mode multilayer neural network
Author_Institution :
Dept. of Comput. Sci. & Intelligent Syst., Oita Univ., Japan
Abstract :
This paper describes a new pulse mode neuron and multilayer neural network (MNN) with on-chip learning. The proposed neuron and experimental MNN is implemented on field programmable gate array (FPGA) and various experiments are conducted to test the performance of the proposed system. The experimental results show that the proposed neuron has rigid, adjustable nonlinear function and the proposed MNN has good learning performance and generalization capabilities
Keywords :
field programmable gate arrays; generalisation (artificial intelligence); learning (artificial intelligence); multilayer perceptrons; neural chips; adjustable nonlinear function; field programmable gate array; generalization capabilities; learning performance; on-chip learning; pulse mode multilayer neural network; Computer networks; Counting circuits; Field programmable gate arrays; Multi-layer neural network; Neural networks; Neurons; Pulse circuits; Pulse generation; Stochastic processes; Voting;
Conference_Titel :
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-5471-0
DOI :
10.1109/ISCAS.1999.777585
