Skip to main content

Research Repository

Advanced Search

Quantum Dynamic Optimization Algorithm for Neural Architecture Search on Image Classification

Jin, Jin; Zhang, Qian; He, Jia; Yu, Hongnian

Authors

Jin Jin

Qian Zhang

Jia He



Abstract

Deep neural networks have proven to be effective in solving computer vision and natural language processing problems. To fully leverage its power, manually designed network templates, i.e., Residual Networks, are introduced to deal with various vision and natural language tasks. These hand-crafted neural networks rely on a large number of parameters, which are both data-dependent and laborious. On the other hand, architectures suitable for specific tasks have also grown exponentially with their size and topology, which prohibits brute force search. To address these challenges, this paper proposes a quantum dynamic optimization algorithm to find the optimal structure for a candidate network using Quantum Dynamic Neural Architecture Search (QDNAS). Specifically, the proposed quantum dynamics optimization algorithm is used to search for meaningful architectures for vision tasks and dedicated rules to express and explore the search space. The proposed quantum dynamics optimization algorithm treats the iterative evolution process of the optimization over time as a quantum dynamic process. The tunneling effect and potential barrier estimation in quantum mechanics can effectively promote the evolution of the optimization algorithm to the global optimum. Extensive experiments on four benchmarks demonstrate the effectiveness of QDNAS, which is consistently better than all baseline methods in image classification tasks. Furthermore, an in-depth analysis is conducted on the searchable networks that provide inspiration for the design of other image classification networks.

Journal Article Type Article
Acceptance Date Nov 23, 2022
Online Publication Date Nov 30, 2022
Publication Date 2022
Deposit Date Dec 5, 2022
Publicly Available Date Dec 5, 2022
Journal Electronics
Publisher MDPI
Peer Reviewed Peer Reviewed
Volume 11
Issue 23
Article Number 3969
DOI https://doi.org/10.3390/electronics11233969
Keywords quantum dynamics; global optimization; neural architecture search; image classification
Public URL http://researchrepository.napier.ac.uk/Output/2969319

Files




You might also like



Downloadable Citations