Skip to content

spectacles9468/Weight-Sharing-Approach

Repository files navigation

Enhancing Fault-Tolerance in Memristor Crossbar-Based Neural Network

Appendix for Master's thesis

This repository is an appendix to the master's thesis mentionned above. It contains the code used for the experimental analysis of the weight sharing approach to improve fault tolerance of memristor crossbar-based neural network.

Python Notebooks

Neural Network for MNIST.ipynb: It contains the code for a simple neural network consisting of two linear layers for digit recognition of MNIST dataset. Layers vs Single Layer.ipynb: This contains the code for implementating the weights having different fault percentages between 0 to 14% for Single layer memristor crossbar and triple layer memristor crossbar and stores the result in CSV format.

About

Appendix for Master's thesis

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors