Back to Search
Start Over
EGFA-NAS: a neural architecture search method based on explosion gravitation field algorithm.
- Source :
- Complex & Intelligent Systems; Apr2024, Vol. 10 Issue 2, p1667-1687, 21p
- Publication Year :
- 2024
-
Abstract
- Neural architecture search (NAS) is an extremely complex optimization task. Recently, population-based optimization algorithms, such as evolutionary algorithm, have been adopted as search strategies for designing neural networks automatically. Various population-based NAS methods are promising in searching for high-performance neural architectures. The explosion gravitation field algorithm (EGFA) inspired by the formation process of planets is a novel population-based optimization algorithm with excellent global optimization capability and remarkable efficiency, compared with the classical population-based algorithms, such as GA and PSO. Thus, this paper attempts to develop a more efficient NAS method, called EGFA-NAS, by utilizing the work mechanisms of EGFA, which relaxes the search discrete space to a continuous one and then utilizes EGFA and gradient descent to optimize the weights of the candidate architectures in conjunction. To reduce the computational cost, a training strategy by utilizing the population mechanism of EGFA-NAS is proposed. In addition, a weight inheritance strategy for the new generated dust individuals is proposed during the explosion operation to improve performance and efficiency. The performance of EGFA-NAS is investigated in two typical micro search spaces: NAS-Bench-201 and DARTS, and compared with various kinds of state-of-the-art NAS competitors. The experimental results demonstrate that EGFA-NAS is able to match or outperform the state-of-the-art NAS methods on image classification tasks with remarkable efficiency improvement. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 21994536
- Volume :
- 10
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- Complex & Intelligent Systems
- Publication Type :
- Academic Journal
- Accession number :
- 176338970
- Full Text :
- https://doi.org/10.1007/s40747-023-01230-0