Ning Lyu — accepted AI-conference papers

2024

Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View

Anlan Yu, Shusen Jing, Ning Lyu, Wujie Wen, Zhiyuan Yan

NeurIPS 2024poster

Error correcting output code (ECOC) is a classic method that encodes binary classifiers to tackle the multi-class classification problem in decision trees and neural networks. Among ECOCs, the one-hot code has become the default choice in modern deep neural networks (DNNs) due to its simplicity in d…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects

Anlan Yu, Ning Lyu, Jieming Yin, Zhiyuan Yan, Wujie Wen

ICML 2023poster

Error correcting output codes (ECOCs) have been proposed to improve the robustness of deep neural networks (DNNs) against hardware defects of DNN hardware accelerators. Unfortunately, existing efforts suffer from drawbacks that would greatly impact their practicality: 1) robust accuracy (with defect…

Cited by 3 Source ↗PDF ↗Scholar ↗