Factory > Showcase > Probabilistic Fault Tolerance of Neural Networks in the Continuous Limit
Name:
Probabilistic Fault Tolerance of Neural Networks in the Continuous Limit
Description:
Regularizer for failing neurons
Professor — Lab:
Rachid Guerraoui — Distributed Computing Lab
Layman description:
How is a neural network changing its output in presence of failing node? This project provides a regularizer adapting itself to changing conditions.
Papers:
Project status:
inactive — entered showcase: 2022-07-04 — entry updated: 2024-03-22
Source code:
Lab GitHub - last commit: 2020-11-24
Code quality:
This project has not yet been evaluated by the C4DT Factory team. We will be happy to evaluate it upon request.
Project type:
Library
Programming language:
Python
License:
other