activity
20122020
most citedBalanced Modulation for Nonvolatile Memories

17 citations · 27 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2020

CodNN -- Robust Neural Networks From Coded Classification

Netanel Raviv, Siddharth Jain, Pulakesh Upadhyaya +2

Deep Neural Networks (DNNs) are a revolutionary force in the ongoing information revolution, and yet their intrinsic properties remain a mystery. In particular, it is widely known…

cs.IT20202 cited

Functional Error Correction for Robust Neural Networks

Kunping Huang, Paul Siegel, Anxiao +1

When neural networks (NeuralNets) are implemented in hardware, their weights need to be stored in memory devices. As noise accumulates in the stored weights, the NeuralNet's perfor…

cs.IT20197 cited

Machine Learning for Error Correction with Natural Redundancy

Pulakesh Upadhyaya, Anxiao Jiang

The persistent storage of big data requires advanced error correction schemes. The classical approach is to use error correcting codes (ECCs). This work studies an alternative appr…

cs.IT2018

Representation-Oblivious Error Correction by Natural Redundancy

Pulakesh Upadhyaya, Anxiao, Jiang

Storage systems have a strong need for substantially improving their error correction capabilities, especially for long-term storage where the accumulating errors can exceed the de…

cs.CV2018

U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

Ramakrishna Prabhu, Xiaojing Yu, Zhangyang Wang +3

This paper studies the challenging problem of fingerprint image denoising and inpainting. To tackle the challenge of suppressing complicated artifacts (blur, brightness, contrast,…

cs.IT201217 cited

Balanced Modulation for Nonvolatile Memories

Hongchao Zhou, Anxiao, Jiang +1

This paper presents a practical writing/reading scheme in nonvolatile memories, called balanced modulation, for minimizing the asymmetric component of errors. The main idea is to e…