Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network
Not on the map. Why?
Abstract (arXiv)
We consider a neural network (NN) that may experience memory faults and computational errors. In this paper, we propose a novel real-number-based error correction code (ECC) capable of detecting and correcting both memory errors and computational errors. The proposed approach introduces structures in the form of real-number-based linear constraints on the NN weights to enable error detection and correction, without sacrificing classification performance or increasing the number of real-valued NN parameters.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 34 references that are in the map. First posted on arXiv 21 Jan 2026.
Builds on
10 of 34 references.
References · 10
- 2016Wide Residual Networkscited by 3,057
- 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
- 2018Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Acceleratorcited by 25
- 2018A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Dronescited by 21
- 2020Review and Comparison of Commonly Used Activation Functions for Deep Neural Networkscited by 21
- 2021Robust Adversarial Attacks Against DNN-Based Wireless Communication Systemscited by 12
- 2019In-Place Zero-Space Memory Protection for CNNcited by 9
- 2025L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysiscited by 6
- 2020CodNN -- Robust Neural Networks From Coded Classificationcited by 2
- 2025Acoustic neural networks: Identifying design principles and exploring physical feasibilitycited by 1
Built on by
Not cited yet.