mlsanityData to 14 Oct 2026

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

arXiv 2308.08222 ↗First posted 16 Aug 2023cs.RO cs.LGcited by 0

Not on the map. Why?

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.

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

21 of 63 references.

References · 21

  1. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  2. 2016OpenAI Gymcited by 1,736
  3. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  4. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  5. 2019A Theoretical Analysis of Deep Q-Learningcited by 215
  6. 2017Adaptive Neural Networks for Efficient Inferencecited by 163
  7. 2020Training with Quantization Noise for Extreme Model Compressioncited by 145
  8. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 139
  9. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  10. 2019Network Pruning via Transformable Architecture Searchcited by 80
  11. 2020Reinforcement Learning with Quantum Variational Circuitscited by 77
  12. 2020Why should we add early exits to neural networks?cited by 70
9 more
  1. 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
  2. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 65
  3. 2020Classification using Hyperdimensional Computing: A Reviewcited by 60
  4. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 36
  5. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  6. 2021One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latencycited by 17
  7. 2023Inverse Approximation Theory for Nonlinear Recurrent Neural Networkscited by 11
  8. 2022Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networkscited by 6
  9. 2023A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observationscited by 2

Built on by

Not cited yet.