This repository contains the code used in "Genetic Motifs as a Blueprint for Mismatch-Tolerant Neuromorphic Computing".
Note
The code provided in this repository is experimental and intended as a resource for readers interested in studying the methodology proposed. Please note that some of the terminology used in the code may differ from that used in the paper.
Below is a brief description of the main files included in the repository:
models.py: Implementation of the proposed mismatch-tolerant architecture and of the spiking MLP used as baseline.train.py: Script for training the models.
@misc{boccato2024geneticmotifsblueprintmismatchtolerant,
title={Genetic Motifs as a Blueprint for Mismatch-Tolerant Neuromorphic Computing},
author={Tommaso Boccato and Dmitrii Zendrikov and Nicola Toschi and Giacomo Indiveri},
year={2024},
eprint={2410.19403},
archivePrefix={arXiv},
primaryClass={cs.NE},
url={https://arxiv.org/abs/2410.19403},
}
