Séminaire ETIS-CELL – Aurélique Saulquin

Orateur : Aurélique Saulquin (CRIStAL, Université de Lille)

Title: Spiking Neural Network emulation on FPGA for low-power AI

Abstract:

AI, and particularly ANNs have become central to modern computing with remarkable performances for complex task resolution. However, deploying ANNs on embedded systems remains challenging due to their complexity. Neuromorphic computing, and especially Spiking
Neural Networks (SNNs) offers an alternative solution, drawing inspiration from the brain.
Although promising, neuromorphic chips are limited and poorly reconfigurable, making FPGAs an interesting target for research and embedded low-power classification tasks.
In this context, we develop ModNEF, an open-source modular FPGA architecture for SNN inference. Modnef is based on the interconnection of independent modules, offering high implementation flexibility and control. ModNEF was validated with standard neuromorphic
datasets and with a use case for sperm whale detection in the Mediterranean Sea.

Team link: https://teams.microsoft.com/meet/31942320814023?p=pSkW9xXckmBVCDlmqr
Meeting ID: 319 423 208 140 23
Passcode: zJ9Yp2wz