https://github.com/candlelabai/memristorrobustnesstononideality

Code accompanying our manuscript on Enhancing memristor robustness to non-idealities

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (4.8%) to scientific vocabulary

Last synced: 10 months ago · JSON representation

Repository

Code accompanying our manuscript on Enhancing memristor robustness to non-idealities

Created about 1 year ago · Last pushed about 1 year ago

Readme

Code accompanying our manuscript on Enhancing memristor robustness to non-idealities

There are two folders containing the code for training and testing of three different datastes; FMNIST, NMNIST, and DVS128Gesture.
It takes quite some time to train the netwokrs, therefore each test folder also includes pretrained models. There are a total of 6 trained model files in each folder; one trained in normal way and the other five with different levels of noise.
Please note that testing requires the 'AIHWKIT' installation and this library is only available for linux[1].

[1] https://github.com/IBM/aihwkit