# NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes

arXiv: https://arxiv.org/abs/2306.16869 · HTML: https://mlsanity.com/paper/2306.16869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning](https://mlsanity.com/paper/1611.05128/) (2016)
- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)
- [Batch-Shaping for Learning Conditional Channel Gated Networks](https://mlsanity.com/paper/1907.06627/) (2019)
- [EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM](https://mlsanity.com/paper/1910.05340/) (2019)
- [ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model](https://mlsanity.com/paper/1812.01803/) (2018)
- [Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking](https://mlsanity.com/paper/1806.04321/) (2018)
- [Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks](https://mlsanity.com/paper/1602.08556/) (2016)

## Built on by (most cited first, 2 of 2)

- [SafeCiM: Investigating Resilience of Hybrid Floating-Point Compute-in-Memory Deep Learning Accelerators](https://mlsanity.com/paper/2512.00059/) (2025)
- [SPINE: A Fault Injection Profiler for Quantized Neural Networks under Accumulated Faults](https://mlsanity.com/paper/2606.19526/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have become ubiquitous in machine learning, but their energy consumption remains problematically high. An effective strategy for reducing such consumption is supply-voltage reduction, but if done too aggressively, it can lead to accuracy degradation. This is due to random bit-flips in static random access memory (SRAM), where model parameters are stored. To address this challenge, we have developed NeuralFuse, a novel add-on module that handles the energy-accuracy tradeoff in low-voltage regimes by learning input transformations and using them to generate error-resistant data representations, thereby protecting DNN accuracy in both nominal and low-voltage scenarios. As well as being easy to implement, NeuralFuse can be readily applied to DNNs with limited access, such cloud-based APIs that are accessed remotely or non-configurable hardware. Our experimental results demonstrate that, at a 1% bit-error rate, NeuralFuse can reduce SRAM access energy by up to 24% while recovering accuracy by up to 57%. To the best of our knowledge, this is the first approach to addressing low-voltage-induced bit errors that requires no model retraining.