Title :
CMOS circuit implementations for neuron models
Author :
Linares-Barranco, Bernabé ; Sánchez-Sinencio, Edgar ; Rodriguez-Vasquez, A.
Author_Institution :
Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
Abstract :
The mathematical neuron basic cells used as basic cells in popular neural network architectures and algorithms are discussed. The most popular neuron models (without training) used in neural network architectures and algorithms (NNA) are considered, focusing on hardware implementation of neuron models used in NAA, and in emulation of biological systems. Mathematical descriptions and block diagram representations are utilized in an independent approach. Nonoscillatory and oscillatory models are discussed
Keywords :
CMOS integrated circuits; computer architecture; neural nets; CMOS circuit implementations; NAA; emulation; mathematical neuron basic cells; neural network architectures; neuron models; nonoscillatory models; oscillatory models; Artificial neural networks; Biological system modeling; CMOS technology; Circuits; Differential equations; Hardware; Network topology; Neural networks; Neurons; Semiconductor device modeling;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112499
