A Study of Deep Learning Robustness Against Computation Failures

2017/04/18 by J Vialatte, Vialatte, Jean-Charles, François Leduc-Primeau +1 · 1 citation
Computer Science · Engineering · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Radiation Effects in Electronics

paper · doi:10.48550/arxiv.1704.05396

openalex publication_date 2017/04/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

For many types of integrated circuits, accepting larger failure rates in computations can be used to improve energy efficiency. We study the performance of faulty implementations of certain deep neural networks based on pessimistic and optimistic models of the effect of hardware faults. After identifying the impact of hyperparameters such as the number of layers on robustness, we study the ability of the network to compensate for computational failures through an increase of the network size. We show that some networks can achieve equivalent performance under faulty implementations, and quantify the required increase in computational complexity.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Gradient-based learning applied to document recognition
• Multilayer feedforward networks are universal approximators

Cited by

• On the security relevance of weights in deep learning

Related

• Special Session: Approximation and Fault Resiliency of DNN Accelerators
• On the Resilience of Deep Learning for Reduced-voltage FPGAs
• Towards Dynamic Fault Tolerance for Hardware-Implemented Artificial Neural Networks: A Deep Learning Approach
• Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
• FAT: Training Neural Networks for Reliable Inference Under Hardware\n Faults