KHACEF , Lyes

Ma thèse en 180 secondes

The brain's cortical plasticity is one of the main features that enable our capability to learn and adapt in our environment. Indeed, the cerebral cortex has the ability to self-organize itself through two distinct forms of plasticity: the structural plasticity that creates (sprouting) or cuts (pruning) synaptic connections between neurons, and...

Encadré par Benoit Miramond

Les réseaux de neurones connaissent aujourd'hui un engouement sans précédent grâce à l'explosion de l'open data et de la puissance de calcul toujours plus importante des ordinateurs actuels. Cependant, diverses applications telles que la reconnaissance de la voix ou la détection et classification d'objets nécessitent une implémentation...

Self-organization is a powerful bio-inspired feature that has been poorly investigated in the context of hardware computing architectures. The neural foundations of brain selforganization enable structural plasticity, continuous learning,and tolerance to lesions but at the cost of massive lateralsynaptic connections. A cellular formulation of...

Artificial neural networks are experiencing today an unprecedented interest thanks to two main changes: the explosion of open data that is necessary for their training, and the increasing computing power of today's computers that makes the training part possible in a reasonable time. The recent results of deep neural networks on image...

Local plasticity mechanisms enable our brains to self-organize, both in structure and function, in order to adapt to the environment. This unique property is the inspiration for this study: we propose a brain-inspired computational model for self-organization, then discuss its impact on theclassification accuracy and the energy-efficiency of an...

Few-shot classification is a challenge in machine learning where the goal is to train a classifier using a very limited number of labeled examples. This scenario is likely to occur frequently in real life, for example when data acquisition or labeling is expensive. In this work,we consider the problem of post-labeled few-shot unsupervised...

Cortical plasticity is one of the main features that enable our capability to learn and adapt in our environment. Indeed, the cerebral cortex has the ability to self-organize itself through two distinct forms of plasticity: the structural plasticity that creates (sprouting) or cuts (pruning) synaptic connections between neurons, and the...

Our brain-inspired computing approach attempts to simultaneously reconsider AI and von Neumann's architecture. Both are formidable tools responsible for digital and societal revolutions, but also intellectual bottlenecks linked to the ever-present desire to ensure the system is under control. The brain remains our only reference in terms of...

The written and spoken digits database is not a new database but a constructed database from existing ones, in order to provide a ready-to-use database for multimodal fusion.The written digits database is the original MNIST handwritten digits database [1] with no additional processing. It consists of 70000 images (60000 for training and 10000...

The Self-Organizing Map (SOM) is a brain-inspired neural model that is very promising for unsupervised learning, especially in embedded applications. However, it is unable to learn efficient prototypes when dealing with complex datasets. We propose in this work to improve the SOM performance by using extracted features instead of raw data. We...

Cortical plasticity is one of the main features that enable our capability to learn and adapt in our environment. Indeed, the cerebral cortex has the ability to self-organize itself through two distinct forms of plasticity: the structural plasticity that creates (sprouting) or cuts (pruning) synaptic connections between neurons, and the...

Cortical plasticity is one of the main features that enable our capability to learn and adapt in our environment. Indeed, the cerebral cortex has the ability to self-organize itself through two distinct forms of plasticity: the structural plasticity that creates (sprouting) or cuts (pruning) synaptic connections between neurons, and the...

Machine learning has recently taken the leading role in machine vision through deep learning algorithms. It has brought the best results in object detection, recognition and tracking. Nevertheless, these systems are computationally expensive since they need to process the whole images from the camera for producing such results. Consequently,...

During the last years, Deep Neural Networks have reached the highest performances in image classification Nevertheless,such a success is mostly based on supervised and off-line learning: they require thus huge labeled datasets for learning,and once it is done, they cannot adapt to any change in the data from the environment. In the context of...

Les réseaux de capteurs sans fil connaissement aujourd'hui un engouement sans précédent, notamment dans le cadre des Smart Cities, et cela conduit à l'explosion de leur consommation, et exige d'optimiser les algorithmes de Machines Learning, et notamment les réseaux de neurones qui se sont imposés de par leur capacité d'apprentissage et leur...

The discrimination of human gestures using wearable solutions is extremely important as a supporting technique for assisted living, healthcare of the elderly and neurorehabilitation. This paper presents a mobile electromyography (EMG)analysis framework to be an auxiliary component in physiotherapy sessions or as a feedback for neuroprosthesis...

This paper presents the self-organized neuromorphic architecture named SOMA. The objective is to study neural-based self-organization in computing systems and to prove the feasibility of a self-organizing hardware structure. Considering that these properties emerge from large scale and fully connected neural maps, we will focus on the...

The demonstration shows a mobile application, called "RELAX", for hand gesture classification using multi-sensors fusion. In particular, we integrated the data collected by an electromyography (EMG) sensor with the events produced by an event-based vision sensor, the Dynamic Vision Sensor (DVS). The application runs real-time on any Android...

This paper presents an approach based on Machine Learning (ML) to estimate the performance of small antennas inpractical applications. As a proof of concept, the case of printed antennas integrated into compact terminals, such as for Internet of Things (IoT) or 5G applications, is considered.

Cet article présente une approche basée sur l'apprentissage automatique (ML) pour estimer les limites de performances d'antennes miniatures dans le cas d'applications pratiques. Cette étude considère des antennes imprimées à F-inversé (IFA) intégrées dans des terminaux compacts tels que ceux utilisés pour l'Internet des Objets (IoT) ou les...

article dans Nice Matin page Santé relatif à la "Semaine du cerveau"

The field of artificial intelligence has significantly advanced over the past decades, inspired by discoveries from the fields of biology and neuroscience. The idea of this work is inspired by the process of self-organization of cortical areas in the human brain from both afferent and lateral/internal connections. In this work, we develop an...