# EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems

arXiv: https://arxiv.org/abs/2304.04039 · HTML: https://mlsanity.com/paper/2304.04039/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 75 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 30 of 33)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition](https://mlsanity.com/paper/1710.04734/) (2017)
- [T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding](https://mlsanity.com/paper/2003.11741/) (2020)
- [BindsNET: A machine learning-oriented spiking neural networks library in Python](https://mlsanity.com/paper/1806.01423/) (2018)
- [Q-SpiNN: A Framework for Quantizing Spiking Neural Networks](https://mlsanity.com/paper/2107.01807/) (2021)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2007.08860/) (2020)
- [SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments](https://mlsanity.com/paper/2103.00424/) (2021)
- [EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM](https://mlsanity.com/paper/1910.05340/) (2019)
- [SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron](https://mlsanity.com/paper/1903.02440/) (2019)
- [ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories](https://mlsanity.com/paper/2108.10271/) (2021)
- [SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors](https://mlsanity.com/paper/2203.05523/) (2022)
- [lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents](https://mlsanity.com/paper/2205.12295/) (2022)
- [A Survey on Edge Computing Systems and Tools](https://mlsanity.com/paper/1911.02794/) (2019)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [MorphIC: A 65-nm 738k-Synapse/mm2 Quad-Core Binary-Weight Digital Neuromorphic Processor with Stochastic Spike-Driven Online Learning](https://mlsanity.com/paper/1904.08513/) (2019)
- [Unsupervised Learning with Self-Organizing Spiking Neural Networks](https://mlsanity.com/paper/1807.09374/) (2018)
- [ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators](https://mlsanity.com/paper/1902.10222/) (2019)
- [DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks](https://mlsanity.com/paper/2004.10341/) (2020)
- [Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equations](https://mlsanity.com/paper/1904.11263/) (2019)
- [STDP Learning of Image Patches with Convolutional Spiking Neural Networks](https://mlsanity.com/paper/1808.08173/) (2018)
- [Understanding Reduced-Voltage Operation in Modern DRAM Chips: Characterization, Analysis, and Mechanisms](https://mlsanity.com/paper/1705.10292/) (2017)
- [PiDRAM: A Holistic End-to-end FPGA-based Framework for Processing-in-DRAM](https://mlsanity.com/paper/2111.00082/) (2021)

## Built on by (most cited first, 6 of 6)

- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack](https://mlsanity.com/paper/2404.03325/) (2024)
- [SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents](https://mlsanity.com/paper/2404.09331/) (2024)
- [FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systems](https://mlsanity.com/paper/2407.05262/) (2024)
- [SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Models](https://mlsanity.com/paper/2510.15566/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have shown capabilities of achieving high accuracy under unsupervised settings and low operational power/energy due to their bio-plausible computations. Previous studies identified that DRAM-based off-chip memory accesses dominate the energy consumption of SNN processing. However, state-of-the-art works do not optimize the DRAM energy-per-access, thereby hindering the SNN-based systems from achieving further energy efficiency gains. To substantially reduce the DRAM energy-per-access, an effective solution is to decrease the DRAM supply voltage, but it may lead to errors in DRAM cells (i.e., so-called approximate DRAM). Towards this, we propose textitEnforceSNN, a novel design framework that provides a solution for resilient and energy-efficient SNN inference using reduced-voltage DRAM for embedded systems. The key mechanisms of our EnforceSNN are: (1) employing quantized weights to reduce the DRAM access energy; (2) devising an efficient DRAM mapping policy to minimize the DRAM energy-per-access; (3) analyzing the SNN error tolerance to understand its accuracy profile considering different bit error rate (BER) values; (4) leveraging the information for developing an efficient fault-aware training (FAT) that considers different BER values and bit error locations in DRAM to improve the SNN error tolerance; and (5) developing an algorithm to select the SNN model that offers good trade-offs among accuracy, memory, and energy consumption. The experimental results show that our EnforceSNN maintains the accuracy (i.e., no accuracy loss for BER less-or-equal 10^-3) as compared to the baseline SNN with accurate DRAM, while achieving up to 84.9% of DRAM energy saving and up to 4.1x speed-up of DRAM data throughput across different network sizes.