Linear and Nonlinear Electrical Models of Neurons for Hopfield Neural Network

• Published in: Zeitschrift für Naturforschung. A, A journal of physical sciences Vol. 71; no. 11; pp. 995 - 1002
• Main Authors: Sarwar, Farah, Iqbal, Shaukat, Hussain, Muhammad Waqar
• Format: Journal Article
• Language: English
• Published: De Gruyter 01.11.2016
• Subjects: Hopfield Neural Network; Linear/Nonlinear Model; Neural Network Hardware; Neural Network Processing
• ISSN: 0932-0784; 1865-7109; 1865-7109
• DOI: 10.1515/zna-2016-0161

A novel electrical model of neuron is proposed in this presentation. The suggested neural network model has linear/nonlinear input-output characteristics. This new deterministic model has joint biological properties in excellent agreement with the earlier deterministic neuron model of Hopfield and Tank and to the stochastic neuron model of McCulloch and Pitts. It is an accurate portrayal of differential equation presented by Hopfield and Tank to mimic neurons. Operational amplifiers, resistances, capacitor, and diodes are used to design this system. The presented biological model of neurons remains to be advantageous for simulations. Impulse response is studied and conferred to certify the stability and strength of this innovative model. A simple illustration is mapped to demonstrate the exactness of the intended system. Precisely mapped illustration exhibits 100 % accurate results.