Finite Impulse Response (FIR) Filter Model of Synapses: Associated Neural Networks

Author

Garimella, Rama Murthy

Author_Institution

Commun. & Networking Res. Centre, Int. Inst. of Inf. Technol., Hyderabad

Volume

2

fYear

2008

fDate

18-20 Oct. 2008

Firstpage

370

Lastpage

374

Abstract

In this research paper, based on biological motivation, synapse is modeled as a Finite Impulse Response (FIR) linear filter. Motivation for the concept of robust neural networks is proposed. A novel incremental gradient based learning algorithm is derived (to update the FIR filter coefficients in successive slots). This model of neuron is utilized for arriving at a multi-layer perceptron. Also, a potential associative memory based on FIR filter model of synapse is proposed. Briefly the novel model of neuron is compared with the traditional model of neuron. It is reasoned that the traditional model of neuron is very restrictive.

Keywords

FIR filters; electrical engineering computing; gradient methods; learning (artificial intelligence); multilayer perceptrons; FIR linear filter; associated neural networks; associative memory; finite impulse response filter; incremental gradient based learning algorithm; multilayer perceptron; synapse; Artificial neural networks; Biological neural networks; Biological system modeling; Convolution; Finite impulse response filter; Information filtering; Information filters; Neural networks; Neurons; Nonlinear filters; FIR filter; dynamic synapse; incremental gradient learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation, 2008. ICNC '08. Fourth International Conference on

Conference_Location

Jinan

Print_ISBN

978-0-7695-3304-9

Type

conf

DOI

10.1109/ICNC.2008.910

Filename

4667019