INSTITUTIONAL DIGITAL REPOSITORY

Python-LTspice co-simulation to train neural networks with memristive synapses to learn logic gate operations

Show simple item record

dc.contributor.author Kumar, S.
dc.contributor.author Das, D.M.
dc.date.accessioned 2022-08-25T14:58:54Z
dc.date.available 2022-08-25T14:58:54Z
dc.date.issued 2022-08-25
dc.identifier.uri http://localhost:8080/xmlui/handle/123456789/3897
dc.description.abstract Neuromorphic computing attempts to mimic the neural architecture of human brain by delivering a non vonNeumann hardware which can run even the most complex artificial intelligence algorithms at extremely fast computational speeds at power requirement as low in order as few tens of watts just like the human brain does. Since the brain is a complex mesh of millions of neurons communicating via the synapses and spiking signals in between them, there is a requirement of a circuit based memory element which can play the role of these synapses in electronic circuits. The memristors with there unique pinched hysteresis property have been proposed and modelled to act as these synapses. This paper introduces LTspice modelling of a simple artificial neural network with memristive synapses and training it for the universal gates-NOR and NAND by providing a mechanism for interpreting the compressed binary data generated by parametric LTspice simulations. The results show potential for application in many other crucial neuromorphic simulations and their numeric interpretation using the tool developed for Co-simulation of LTspice with the open source programming language, Python. en_US
dc.language.iso en_US en_US
dc.subject Artificial neural network en_US
dc.subject Crossbar en_US
dc.subject Multilayer perceprtron (MLP) en_US
dc.subject Neuromorphic computing en_US
dc.subject Python-LTspice co-simulation en_US
dc.subject Spiking en_US
dc.subject Universal gate en_US
dc.title Python-LTspice co-simulation to train neural networks with memristive synapses to learn logic gate operations en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account