# HyperSNN: A new efficient and robust deep learning model for resource constrained control applications

arXiv: https://arxiv.org/abs/2308.08222 · HTML: https://mlsanity.com/paper/2308.08222/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 16 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [A Theoretical Analysis of Deep Q-Learning](https://mlsanity.com/paper/1901.00137/) (2019)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Training with Quantization Noise for Extreme Model Compression](https://mlsanity.com/paper/2004.07320/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Defensive Quantization: When Efficiency Meets Robustness](https://mlsanity.com/paper/1904.08444/) (2019)
- [Network Pruning via Transformable Architecture Search](https://mlsanity.com/paper/1905.09717/) (2019)
- [Reinforcement Learning with Quantum Variational Circuits](https://mlsanity.com/paper/2008.07524/) (2020)
- [Why should we add early exits to neural networks?](https://mlsanity.com/paper/2004.12814/) (2020)
- [Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition](https://mlsanity.com/paper/1509.08971/) (2015)
- [HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise](https://mlsanity.com/paper/2110.11417/) (2021)
- [Classification using Hyperdimensional Computing: A Review](https://mlsanity.com/paper/2004.11204/) (2020)
- [A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks](https://mlsanity.com/paper/1905.02704/) (2019)
- [Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters](https://mlsanity.com/paper/2012.05321/) (2020)
- [One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency](https://mlsanity.com/paper/2110.05929/) (2021)
- [Inverse Approximation Theory for Nonlinear Recurrent Neural Networks](https://mlsanity.com/paper/2305.19190/) (2023)
- [Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks](https://mlsanity.com/paper/2211.08410/) (2022)
- [A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations](https://mlsanity.com/paper/2307.02947/) (2023)

## Abstract (arXiv)

In light of the increasing adoption of edge computing in areas such as intelligent furniture, robotics, and smart homes, this paper introduces HyperSNN, an innovative method for control tasks that uses spiking neural networks (SNNs) in combination with hyperdimensional computing. HyperSNN substitutes expensive 32-bit floating point multiplications with 8-bit integer additions, resulting in reduced energy consumption while enhancing robustness and potentially improving accuracy. Our model was tested on AI Gym benchmarks, including Cartpole, Acrobot, MountainCar, and Lunar Lander. HyperSNN achieves control accuracies that are on par with conventional machine learning methods but with only 1.36% to 9.96% of the energy expenditure. Furthermore, our experiments showed increased robustness when using HyperSNN. We believe that HyperSNN is especially suitable for interactive, mobile, and wearable devices, promoting energy-efficient and robust system design. Furthermore, it paves the way for the practical implementation of complex algorithms like model predictive control (MPC) in real-world industrial scenarios.