LEAT Lab – University Cote d’Azur ...Looks like this Team want to explore us a little further
Haven't looked into who or what ANR Project DeepSee is yet - that's where the grant is coming from
- DECEMBER 10, 2022
- COMMENTS OFF
Evaluation of neuromorphic AI with embedded Spiking Neural Networks
Background
AI is proliferating everywhere even to embedded systems to integrate intelligence closer to the sensors (IoT, drones, vehicles, satellites ...). But the energy consumption of current Deep learning solutions makes classical AI hardly compatible with energy and resource constrained devices. Edge AI is a recent subject of research that needs to take into account the cost of the neural models both during the training and during the prediction. An original and promising solution to face these constraints is to merge compression technics of deep neural networks and event-based encoding of information thanks to Spiking neural networks (SNN). SNN are considered as third generation of artificial neural networks and are inspired from the way the information is encoded in the brain, and previous works tend to
conclude that SNN are more efficient than classical deep networks [3]. This internship project aims at confirming this assumption by converting classical CNN to SNN from standard Machine Learning frameworks (Keras) and deploy the resulting neural models onto the Akida neuromorphic processor from BrainChip company [4]. The results obtained in terms of accuracy, latency and energy will be compared to other existing embedded solutions for Edge AI [2].
Project mission
The project mission will be organized in several periods:
References
- Bibliographic study on spiking neural network training
- Introduction to the existing Sw framework from BrainChip
- Training of convolutional neural networks for embedded applications [1] and conversion from CNN to SNN from Keras
- Deployment of the SNN onto Akida processing platform
- Experiments and measurements
- Publication in an international conference.
[1] L Cordone, Miramond B, Thierion, Object Detection with Spiking Neural Networks on Automotive Event Data, IEEE International Joint Conference on Neural Networks (IJCNN), 2022[2] N Abderrahmane, Miramond B, Kervennic E, A Girard, SPLEAT: SPiking Low-power Event-based
ArchiTecture
for in-orbit processing of satellite imagery, IEEE International Joint Conference on Neural Networks, 1-10, 2022
[3] E Lemaire, L Cordone, A Castagnetti, PE Novac, J Courtois, B Miramond, An Analytical Estimation of Spiking
Neural Networks Energy Efficiency, Springer International Conference on Neural Information Processing, 2022[4] T. Álvarez-Sánchez, et al, Detection of facial emotions using neuromorphic computation, Applications of
Digital Image Processing, 2022
Practical information
Location : LEAT Lab / SophiaTech Campus, Sophia Antipolis
Duration : 6 months from march 2023
Grant : from ANR project DeepSee
Profile : Machine learning, Artificial intelligence, Artificial neural networks, Python, Keras, Pytorch
Research keywords : Spiking neural network, Edge AI, neuromorphic computing
Contact and supervision
Benoît Miramond, Andrea Castagnetti
LEAT Lab – University Cote d'Azur / CNRS
Polytech Nice Sophia
04.89.15.44.39. / benoit.miramond@univ-cotedazur.fr
Le LEAT – LEAT
leat.univ-cotedazur.fr
THE LEAT
- Home/
- The LEAT
Presentation
The Laboratory of Electronics, Antennas and Telecommunications (LEAT) is a Joint Unit Université Côte d'Azur – CNRS (UMR n°7248). It is located on the SophiaTech campus, which is a training and research center dedicated to Information and Communication Technologies (ICT) involving academic actors (UNS, INRIA, EURECOM, CNRS, Polytech'Nice Sophia, Mines Paris Tech, etc.), competitiveness clusters, numerous associations and technological platforms.
Management Team
Director: Robert Staraj (PR, UCA)
Deputy Directors: Jean-Marc Ribero (PR, UCA) and François Verdier (PR, UCA)
Administrative Manager: Françoise Trucas (CNRS)
Research activities
Research activities are carried out in the field of telecommunications, radar, e-health, security, smart buildings, earth observation, sustainable development, etc. They are organized into three themes: EDGE (Edge Computing and Digital Systems), CMA (Antenna Design and Modeling) and ISA (Microwave Imaging and Antenna Systems).
Environment
LEAT participates in the activities of the main competitiveness clusters in the region. It is associated with the research program of the "Laboratory of Excellence" Labex UCN@Sophia. Among the partners with which the laboratory is associated, are present the two supervisory bodies (Nice Sophia Antipolis University and the CNRS), but also Eurecom, Inria and the I3S and LTCI laboratories. The Labex is part of the IDEX UCAJEDI.
The Centre de RErecherche Mutualisé sur les ANTennes (CREMANT), created in 2008, is a joint laboratory between the University of Nice Sophia Antipolis (now Université Côte d'Azur), the CNRS and Orange. It allowed the pooling of personnel and equipment between LEAT academic researchers and Orange Labs La Turbie engineers on common research topics (antenna integration, engineering for e-health, multisensor, MIMO and massive MIMO systems, antennas based on new materials, electromagnetic modeling).
tough work ... but someone's gotta do it!
When obstacles emerge along the way, we’ll navigate around them as we always have: with vigilance, pragmatism, and agility.
