← Back to all news
arXiv Machine Learning By Ziqing Lu, Myung Cho, Qiutong Jin, Weiyu Xu

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

Read the original on arXiv Machine Learning →

The paper introduces a real-valued error correction coding framework for neural networks that detects and corrects both memory faults and computational errors. It imposes structured linear constraints on network weights, allowing efficient error detection and recovery without adding parameters or hurting classification performance. The method uses linear programming and sparse recovery to keep error correction low‑complexity, and is claimed to be the first real‑number‑based ECC scheme addressing both error types simultaneously.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 7

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.

By Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag, Allison Seigler, Priscila M. V. Lima, Felipe M. G. Fran\c{c}a, Lizy K. John
efficiencybenchmarkssafety
More like this →
arXiv Machine Learning
Sep 21

Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers

The paper introduces a layerwise, decoupled approach to structurally sparsify fully connected layers in pretrained neural networks. By extracting shallow two‑layer subnetworks, normalizing inner weights, and applying a structured group penalty to each block’s outer weight matrix, the method prunes neurons sequentially and reduces layer widths. The authors prove equivalence to a joint penalty for positively homogeneous activations, and demonstrate that this decoupled formulation is more robust, offering a broader regularization range and lower catastrophic over‑pruning while preserving accuracy in classification, sparse‑recovery, PINN, and OPT‑1.3B experiments.

By Charles Kulick, Armenak Petrosyan, Sui Tang
efficiency
More like this →