SpArNet
Autor: | Orlando Moreira, Arash Pourtaherian, Jonathan Tapson, Mina A. Khoei, Amirreza Yousefzadeh |
---|---|
Přispěvatelé: | Center for Care & Cure Technology Eindhoven, Video Coding & Architectures |
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Spiking neural network
0209 industrial biotechnology Artificial neural network Quantitative Biology::Neurons and Cognition Computer science Distributed computing Inference 02 engineering and technology Convolutional neural network 020901 industrial engineering & automation Neuromorphic engineering Asynchronous communication Gesture recognition 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing SDG 7 - Affordable and Clean Energy SDG 7 – Betaalbare en schone energie Efficient energy use |
Zdroj: | Proceedings-2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020, 256-260 STARTPAGE=256;ENDPAGE=260;TITLE=Proceedings-2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020 AICAS |
Popis: | Biological neurons are known to have sparse and asynchronous communications using spikes. Despite our incomplete understanding of processing strategies of the brain, its low energy consumption in fulfilling delicate tasks suggests the existence of energy efficient mechanisms. Inspired by these key factors, we introduce SpArNet, a bio-inspired quantization scheme to convert a pre-trained convolutional neural network to a spiking neural network, with the aim of minimizing the computational load for execution on neuromorphic processors. The proposed scheme has significant advantages over the reference CNN in a reduced number of synaptic operations, and can be used for frequent executions of inference tasks. The computational load of SpArNet is adjusted to the spatio-temporal dynamics of the the input data. We have tested the converted network on two applications (autonomous steering and hand gesture recognition), demonstrating a significant reduction on the number of required synaptic operations. |
Databáze: | OpenAIRE |
Externí odkaz: |