SpikeExplorer: Hardware-Oriented Design Space Exploration for Spiking Neural Networks on FPGA
Open Access
- 1 May 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (9) , 1744
Abstract
One of today’s main concerns is to bring artificial intelligence capabilities to embedded systems for edge applications. The hardware resources and power consumption required by state-of-the-art models are incompatible with the constrained environments observed in edge systems, such as IoT nodes and wearable devices. Spiking Neural Networks (SNNs) can represent a solution in this sense: inspired by neuroscience, they reach unparalleled power and resource efficiency when run on dedicated hardware accelerators. However, when designing such accelerators, the amount of choices that can be taken is huge. This paper presents SpikExplorer, a modular and flexible Python tool for hardware-oriented Automatic Design Space Exploration to automate the configuration of FPGA accelerators for SNNs. SpikExplorer enables hardware-centric multiobjective optimization, supporting target factors such as accuracy, area, latency, power, and various combinations during the exploration process. The tool searches the optimal network architecture, neuron model, and internal and training parameters leveraging Bayesian optimization, trying to reach the desired constraints imposed by the user. It allows for a straightforward network configuration, providing the full set of explored points for the user to pick the trade-off that best fits their needs. The potential of SpikExplorer is showcased using three benchmark datasets. It reaches 95.8% accuracy on the MNIST dataset, with a power consumption of 180 mW/image and a latency of 0.12 ms/image, making it a powerful tool for automatically optimizing SNNs.Keywords
All Related Versions
Funding Information
- European Commission (101070238, 956090, CN00000013)
- MUR (101070238, 956090, CN00000013)
This publication has 44 references indexed in Scilit:
- Neural Architecture Search for Spiking Neural Networks2022
- AutomaticAI – A hybrid approach for automatic artificial intelligence algorithm selection and hyperparameter tuningExpert Systems with Applications, 2021
- The viability of analog-based accelerators for neuromorphic computing: a surveyNeuromorphic Computing and Engineering, 2021
- Optimization Under Stochastic Uncertainty2020
- Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial IntelligenceNeural Networks, 2020
- Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence2019
- Quantitative investigations of electrical nerve excitation treated as polarizationBiological Cybernetics, 2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997
- Learning representations by back-propagating errorsNature, 1986