Neural Architecture Search for E{cient Convolutional Networks: A Multi-Objective Optimization Approach

Abstract

This paper presents a novel neural architecture search (NAS) framework that optimizes convolutional neural networks for both accuracy and
computational e{ciency. Traditional NAS methods often prioritize accuracy at the expense of computational requirements, making them impractical for resource-constrained environments. Our approach employs
a multi-objective optimization strategy that simultaneously maximizes
classi}cation accuracy while minimizing computational cost, measured in
~oating-point operations (FLOPs). We introduce a hierarchical search
space that enables e{cient exploration of architectural variations and implement a modi}ed evolutionary algorithm with adaptive mutation rates.
Experimental results on CIFAR-10 and ImageNet datasets demonstrate
that our method discovers architectures that achieve competitive accuracy
with state-of-the-art models while reducing computational requirements
by 35-60