我要吃瓜

Live Demonstration: Unlocking the Potential of Two-Point Neuronal Cells for Energy-Efficient Training of Deep Networks

Details

Citation

Adeel A, Adetomi A, Phillips WA, Raza M, Ahmed K, Hussain A & Arslan T (2023) Live Demonstration: Unlocking the Potential of Two-Point Neuronal Cells for Energy-Efficient Training of Deep Networks. In: 2023 IEEE International Symposium on Circuits and Systems (ISCAS), Monterey, CA, USA, 21.05.2023-25.05.2023. IEEE. https://doi.org/10.1109/iscas46773.2023.10181836

Abstract
This paper is the first live demonstration of the transformative computational potential of context-sensitive two-point layer 5 pyramidal cells (L5PCs). We will showcase a Multi-Processor System on Chip (MPSoC)-based implementation of a biologically plausible L5PC-driven deep neural network (DNN), termed multisensory cooperative computing (MCC). This will be shown to effectively process heterogeneous real-world audio-visual data consuming far less energy compared to state-of-the-art ‘point’ neuron-driven DNNs. Our approach opens new cross-disciplinary avenues for future on-chip DNN training implementations and posits a radical shift in current neuromorphic computing paradigms.

StatusPublished
Funders
Publication date31/05/2023
Publication date online31/07/2023
PublisherIEEE
Conference2023 IEEE International Symposium on Circuits and Systems (ISCAS)
Conference locationMonterey, CA, USA
Dates

People (2)

Dr Ahsan Adeel

Dr Ahsan Adeel

Assoc. Prof. in Artificial Intelligence, Computing Science and Mathematics - Division

Professor Bill Phillips

Professor Bill Phillips

Emeritus Professor, Psychology