Concept
Alignement des intelligences artificielles
Publications associées (55)
Overflow-free compute memories for edge AI acceleration
David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Marco Antonio Rios, Flavio Ponzina
Compute memories are memory arrays augmented with dedicated logic to support arithmetic. They support the efficient execution of data-centric computing patterns, such as those characterizing Artificial Intelligence (AI) algorithms. These architectures can ...
2023Bit-Line Computing for CNN Accelerators Co-Design in Edge AI Inference
David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Marco Antonio Rios, Flavio Ponzina
By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional o ...
2023Artificial Neural Network Training on an Optical Processor via Direct Feedback Alignment
Florent Gérard Krzakala, Julien Marcel Daniel Emmanuel Launay
Artificial Neural Networks (ANN) are habitually trained via the back-propagation (BP) algorithm. This approach has been extremely successful: Current models like GPT-3 have O(10 11 ) parameters, are trained on O(10 11 ) words and produce awe-inspiring resu ...
IEEE2023Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection
In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...
Research Publishing2023Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units
This paper proposes a safe reinforcement learning algorithm for generation bidding decisions and unit maintenance scheduling in a competitive electricity market environment. In this problem, each unit aims to find a bidding strategy that maximizes its reve ...
ELSEVIER SCI LTD20233DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping
We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photo-like images of fullbody humans with consistent appearances under different view-angles and body-poses. To tackle the representational and computational challenges in sy ...
Ieee Computer Soc2023Closed-Loop Control of Epidural Electrical Stimulation in Patients with Spinal Cord Injury and Parkinson's Disease
Over the past two decades, epidural electrical stimulation (EES) has transitioned from a treatment for chronic pain to a promising paradigm for ameliorating deficits associated with neurological disorders like spinal cord injury (SCI) and Parkinson's Disea ...
EPFL2023A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers
Petr Motlicek, Juan Pablo Zuluaga Gomez, Amrutha Prasad
In this paper we propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training by integrating different state-of-the-art artificial intelligence (AI)-based tools. The virtual simulation-pilot engine receives spoken ...
MDPI2023BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS
Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...
Los Alamitos2023Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations
Devis Tuia, Olga Fink, Florent Evariste Forest, Hugo Laurent Pascal Porta
Monitoring the cracks in walls, roads and other types of infrastructure is essential to ensure the safety of a structure, and plays an important role in structural health monitoring. Automatic visual inspection allows an efficient, costeffective and safe h ...
Research Publishing2023