Functional Stability of Software-Hardware Neural Network Implementation The NeuroComp Project
By: Bychkov Oleksii, Senysh Taras
Potential Business Impact:
Keeps computer brains working even if parts break.
This paper presents an innovative approach to ensuring functional stability of neural networks through hardware redundancy at the individual neuron level. Unlike the classical Dropout method, which is used during training for regularization purposes, the proposed system ensures resilience to hardware failures during network operation. Each neuron is implemented on a separate microcomputer (ESP32), allowing the system to continue functioning even when individual computational nodes fail.
Similar Papers
Floating-Point Neural Network Verification at the Software Level
Software Engineering
Checks if AI code is safe for important jobs.
Neural networks for neurocomputing circuits: a computational study of tolerance to noise and activation function non-uniformity when machine learning materials properties
Neural and Evolutionary Computing
Makes computer brains work better despite flaws.
Fault Tolerant Reconfigurable ML Multiprocessor
Networking and Internet Architecture
Makes computers learn faster and fix themselves.