Showing cs.NEShow all
2 papers · 1 filter
cs.NE2025
From Hand-Crafted Metrics to Evolved Training-Free Performance Predictors for Neural Architecture Search via Genetic Programming
Quan Minh Phan, Ngoc Hoang Luong
Estimating the network performance using zero-cost (ZC) metrics has proven both its efficiency and efficacy in Neural Architecture Search (NAS). However, a notable limitation of mo…
cs.NE2024
Efficient Multi-Objective Neural Architecture Search via Pareto Dominance-based Novelty Search
An Vo, Ngoc Hoang Luong
Neural Architecture Search (NAS) aims to automate the discovery of high-performing deep neural network architectures. Traditional objective-based NAS approaches typically optimize…