# Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network

arXiv: https://arxiv.org/abs/2602.00076 · HTML: https://mlsanity.com/paper/2602.00076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization](https://mlsanity.com/paper/1803.08680/) (2018)
- [Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator](https://mlsanity.com/paper/1802.04657/) (2018)
- [A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones](https://mlsanity.com/paper/1805.01831/) (2018)
- [Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks](https://mlsanity.com/paper/2010.09458/) (2020)
- [Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems](https://mlsanity.com/paper/2102.00918/) (2021)
- [In-Place Zero-Space Memory Protection for CNN](https://mlsanity.com/paper/1910.14479/) (2019)
- [L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis](https://mlsanity.com/paper/2503.20263/) (2025)
- [CodNN -- Robust Neural Networks From Coded Classification](https://mlsanity.com/paper/2004.10700/) (2020)
- [Acoustic neural networks: Identifying design principles and exploring physical feasibility](https://mlsanity.com/paper/2511.21313/) (2025)

## 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.