HyperSNN: A new efficient and robust deep learning model for resource constrained control applications
This addresses energy efficiency for edge computing in areas like robotics and smart homes, though it appears incremental as it builds on existing SNN and hyperdimensional computing techniques.
The paper tackles the problem of high energy consumption in control applications by introducing HyperSNN, a model combining spiking neural networks and hyperdimensional computing, which achieves comparable accuracy to conventional methods while reducing energy expenditure to 1.36% to 9.96% on AI Gym benchmarks.
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.