# CorrectNet: Robustness Enhancement of Analog In-Memory Computing for Neural Networks by Error Suppression and Compensation

arXiv: https://arxiv.org/abs/2211.14917 · HTML: https://mlsanity.com/paper/2211.14917/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 27 Nov 2022.

## Builds on (most cited first, 5 of 5)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Parseval Networks: Improving Robustness to Adversarial Examples](https://mlsanity.com/paper/1704.08847/) (2017)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [Defensive Quantization: When Efficiency Meets Robustness](https://mlsanity.com/paper/1904.08444/) (2019)

## Built on by (most cited first, 9 of 9)

- [Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures](https://mlsanity.com/paper/2405.04700/) (2024)
- [Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise](https://mlsanity.com/paper/2307.15853/) (2023)
- [Compute-in-Memory based Neural Network Accelerators for Safety-Critical Systems: Worst-Case Scenarios and Protections](https://mlsanity.com/paper/2312.06137/) (2023)
- [TSB: Tiny Shared Block for Efficient DNN Deployment on NVCIM Accelerators](https://mlsanity.com/paper/2406.06544/) (2024)
- [NeFT: Negative Feedback Training to Improve Robustness of Compute-In-Memory DNN Accelerators](https://mlsanity.com/paper/2305.14561/) (2023)
- [Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays](https://mlsanity.com/paper/2508.15685/) (2025)
- [OptINC: Optical In-Network-Computing for Scalable Distributed Learning](https://mlsanity.com/paper/2603.28290/) (2026)
- [Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment](https://mlsanity.com/paper/2606.00741/) (2026)
- [CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation](https://mlsanity.com/paper/2607.08015/) (2026)

## Abstract (arXiv)

The last decade has witnessed the breakthrough of deep neural networks (DNNs) in many fields. With the increasing depth of DNNs, hundreds of millions of multiply-and-accumulate (MAC) operations need to be executed. To accelerate such operations efficiently, analog in-memory computing platforms based on emerging devices, e.g., resistive RAM (RRAM), have been introduced. These acceleration platforms rely on analog properties of the devices and thus suffer from process variations and noise. Consequently, weights in neural networks configured into these platforms can deviate from the expected values, which may lead to feature errors and a significant degradation of inference accuracy. To address this issue, in this paper, we propose a framework to enhance the robustness of neural networks under variations and noise. First, a modified Lipschitz constant regularization is proposed during neural network training to suppress the amplification of errors propagated through network layers. Afterwards, error compensation is introduced at necessary locations determined by reinforcement learning to rescue the feature maps with remaining errors. Experimental results demonstrate that inference accuracy of neural networks can be recovered from as low as 1.69% under variations and noise back to more than 95% of their original accuracy, while the training and hardware cost are negligible.