5 papers
Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
Muhammad Junaid Ali, Smail Niar, El-Ghazali Talbi
Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities. However, deploying them in embedded and edge compu…
NeurOptimisation: The Spiking Way to Evolve
Jorge Mario Cruz-Duarte, El-Ghazali Talbi
The increasing energy footprint of artificial intelligence systems urges alternative computational models that are both efficient and scalable. Neuromorphic Computing (NC) addresse…
Neuromorphic-based metaheuristics: A new generation of low power, low latency and small footprint optimization algorithms
El-ghazali Talbi
Neuromorphic computing (NC) introduces a novel algorithmic paradigm representing a major shift from traditional digital computing of Von Neumann architectures. NC emulates or simul…
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
Florian Felten, Umut Ucak, Hicham Azmani +10
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting object…
An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
Julie Keisler, El-Ghazali Talbi, Sandra Claudel +1
In this paper, we propose an algorithmic framework to automatically generate efficient deep neural networks and optimize their associated hyperparameters. The framework is based on…