Alexandre Valentian

Alexandre Valentian

Auto-generated profile, based on publicly available information

Alexandre Valentian

CEA, LIST, Grenoble, France

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MDManon Dampfhoffer
Manon Dampfhoffer
TMThomas Mesquida
Thomas Mesquida
AVAlexandre Valentian
Alexandre Valentian
LALorena Anghel
Lorena Anghel
With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (SNNs) mimic the dynamics of biological neural networks by distributing information over time through binary spikes. Neuromorphic hardware has emerged to leverage the characteristics of SNNs, such as asynchronous processing and high activation sparsity. Therefore, SNNs have recently gained interest in the machine learning community as a brain-inspired alternative to ANNs for low-power applications. However, the discrete representation of the information makes the training of SNNs by backpropagation-based techniques challenging. In this survey, we review training strategies for deep SNNs targeting deep learning applications such as image processing. We start with methods based on the conversion from an ANN to an SNN and compare these with backpropagation-based techniques. We propose a new taxonomy of spiking backpropagation algorithms into three categories, namely, spatial, spatiotemporal, and single-spike approaches. In addition, we analyze different strategies to improve accuracy, latency, and sparsity, such as regularization methods, training hybridization, and tuning of the parameters specific to the SNN neuron model. We highlight the impact of input encoding, network architecture, and training strategy on the accuracy–latency tradeoff. Finally, in light of the remaining challenges for accurate and efficient SNN solutions, we emphasize the importance of joint hardware–software codevelopment.

25 October 2022 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
MDManon Dampfhoffer
Manon Dampfhoffer
TMThomas Mesquida
Thomas Mesquida
AVAlexandre Valentian
Alexandre Valentian
LALorena Anghel
Lorena Anghel
Spiking Neural Networks (SNNs) hold the promise of lower energy consumption in embedded hardware due to their spike-based computations compared to traditional Artificial Neural Networks (ANNs). The relative energy efficiency of this emerging technology compared to traditional digital hardware has not been fully explored. Many studies do not consider memory accesses, which account for an important fraction of the energy consumption, use naive ANN hardware implementations, or lack generality. In this paper, we compare the relative energy efficiency of classical digital implementations of ANNs with novel event-based SNN implementations based on variants of the Integrate and Fire (IF) model. We provide a theoretical upper bound on the relative energy efficiency of ANNs, by computing the maximum possible benefit from ANN data reuse and sparsity. We also use the Eyeriss ANN accelerator as a case study. We show that the simpler IF model is more energy-efficient than the Leaky IF and temporal continuous synapse models. Moreover, SNNs with the IF model can compete with efficient ANN implementations when there is a very high spike sparsity, i.e. between 0.15 and 1.38 spikes per synapse per inference, depending on the ANN implementation. Our analysis shows that hybrid ANN-SNN architectures, leveraging a SNN event-based approach in layers with high sparsity and ANN parallel processing for the others, are a promising new path for further energy savings.

2 September 2022 in IEEE Journal of Solid-State Circuits
Verified
Journal Article
Closed access
Ivan Miro-PanadesIvan Miro-Panades
Ivan Miro-Panades
BTBenoit Tain
Benoit Tain
JCJean-Frédéric CHRISTMANN
Jean-Frédéric CHRISTMANN
DCDavid Coriat
David Coriat
RLRomain Lemaire
Romain Lemaire
FCFabien Clermidy
Fabien Clermidy
Increased capabilities, such as recognition and self-adaptability, are now required from Internet-of-Things (IoT) applications. While IoT node power consumption is a major concern for these applications, cloud-based processing is becoming unsustainable due to continuous sensor or image data transmission over the wireless network. Thus, optimized ML capabilities and data transfers should be integrated into the IoT node. Moreover, IoT applications are torn between sporadic data-logging and energy-hungry data processing (e.g., image classification). Thus, the versatility of the node is key in addressing this wide diversity of energy and processing needs. This article presents SamurAI, a versatile IoT node bridging this gap in processing and energy by leveraging two on-chip sub-systems: a low-power, clock-less, event-driven always-responsive (AR) part and an energy-efficient on-demand (OD) part. AR contains a 1.7-MOPS event-driven, asynchronous Wake-up Controller (WuC) with a 207-ns wake-up time optimized for sporadic computing, while OD combines a deep-sleep RISC-V CPU and 1.3-TOPS/W machine learning (ML) for more complex tasks up to 36 GOPS. This architecture partitioning achieves the best-in-class versatility metrics, such as peak performance to idle power ratio. On an applicative classification scenario, it demonstrates system power gains, up to $3.5\times $ , compared to cloud-based processing, and, thus, extended battery lifetime.


1 June 2008
Verified
Conference Paper
Closed access
EBE. Beigne
E. Beigne
FCF. Clermidy
F. Clermidy
JDJ. Durupt
J. Durupt
HLH. Lhermet
H. Lhermet
SMS. Miermont
S. Miermont
PVP. Vivet
P. Vivet
A fully power aware globally asynchronous locally synchronous network-on-chip circuit is presented in this paper. The circuit is arranged around an asynchronous network-on-chip providing a 17 Gbits/s throughput and automatically reducing its power consumption by activity detection. Both dynamic and static power consumptions are globally reduced using adaptive design techniques applied locally for each NoC units. The dynamic power consumption can be reduced up to a factor of 8 while the static power consumption is reduced by 2 decades in stand-by mode.

1 October 2013
Verified
Conference Paper
Closed access
BPBertrand Pelloux-Prayer
Bertrand Pelloux-Prayer
MBMilovan Blagojevic
Milovan Blagojevic
SHSebastien Haendler
Sebastien Haendler
AVAlexandre Valentian
Alexandre Valentian
AAAmara Amara
Amara Amara
PFPhilippe Flatresse
Philippe Flatresse
UTBB FD-SOI technology is able to reach very high speeds thanks to flip-Wells variant which enables low-V T (LVT) tuning. This approach appears to be the best design option to catch high CPU frequencies or/and optimal energy consumption. To save power when logical paths are not critical, regular-V T (RVT) transistors, which seat on classical-Wells, cannot be abutted to LVT transistors because of the Well bias conflicts. To overcome these multi-V T constraints, several innovative cointegration schemes based on single-Well (SW) approaches have been designed in 28nm UTBB FD-SOI technology and validated by silicon results.