Open AccessDesign of Memristive Hopfield Neural Network using Memristor Bridges
Author(s) -
P. Monurajan,
A Ruhanbevi,
J. Manjula
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.12.16447
Subject(s) - memristor , content addressable memory , artificial neural network , computer science , hopfield network , physical neural network , artificial intelligence , bidirectional associative memory , associative property , topology (electrical circuits) , recurrent neural network , types of artificial neural networks , electronic engineering , mathematics , engineering , electrical engineering , pure mathematics
Artificial Neural Networks are interconnection of neurons inspired from the biological neural network of the brain. ANN is claimed to rule the future, spreads its wings to various areas of interest to name a few such as optimization, information technology, cryptography, image processing and even in medical diagnosis. There are devices which possess synaptic behaviour, one such device is memristor. Bridge circuit of memristors can be combined together to form neurons. Neurons can be made into a network with appropriate parameters to store data or images. Hopfield neural networks are chosen to store the data in associative memory. Hopfield neural networks are a significant feature in ANN which are recurrent in nature and in general are used as associative memory and in solving optimization problems such as the Travelling Salesman Problem. The paper deals on the construction of memristive Hopeld neural network using memristor bridging circuit and its application in the associative memory. This paper also illustrates the experiment with mathematical equations and the associative memory concept of the network using Matlab.