← Search

Erik Goodman

2 accepted papers

2020

NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm (Extended Abstract)

IJCAI 2020poster

Convolutional neural networks (CNNs) are the backbones of deep learning paradigms for numerous vision tasks. Early advancements in CNN architectures are primarily driven by human expertise and elaborate design. Recently, neural architecture search (NAS) was proposed with the aim of automating the ne…

Cited by 0SourcePDFScholar
2020

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

ECCV 2020poster

In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives. It comprises of two surrogates, one at the architecture level to improve sample efficiency and one at the weights level, through a supernet, to improve g…