Can GPT-4 Perform Neural Architecture Search?. (arXiv:2304.10970v1 [cs.LG])

We investigate the potential of GPT-4~\cite{gpt4} to perform Neural
Architecture Search (NAS) -- the task of designing effective neural
architectures. Our proposed approach, \textbf{G}PT-4 \textbf{I}nformed
\textbf{N}eural \textbf{A}rchitecture \textbf{S}earch (GINAS),leverages the
generative capabilities of GPT-4 as a black-box optimiser to quickly navigate
the architecture search space, pinpoint promising candidates, and iteratively
refine these candidates to improve performance.We assess GINAS across several
benchmarks, comparing it with existing state-of-the-art NAS techniques to
illustrate its effectiveness. Rather than targeting state-of-the-art
performance, our objective is …

architecture architectures art arxiv benchmarks box generative gpt gpt-4 gpt4 highlight nas neural architectures neural architecture search performance research search space state technical