Grammatical structure detection by instinct plasticity based echo state networks with genetic algorithm

Liu, Zongying and Li, Shaoxi and Pan, Mingyang and Loo, Chu Kiong (2022) Grammatical structure detection by instinct plasticity based echo state networks with genetic algorithm. Neurocomputing, 467. pp. 173-183. ISSN 0925-2312, DOI https://doi.org/10.1016/j.neucom.2021.09.073.

Full text not available from this repository.

Abstract

A novel model called Instinct Plasticity Echo State Network with New Weights Selection Method, which is Optimized by Genetic Algorithm, is proposed (IP-NESN-GA). There are three proposed methods that are employed in the conventional ESN. New weights selection method provides a novel approach to replace the random weights of ESN, which obtains much better performance than the conventional ESN. At the same time, Instinct Plasticity is successfully applied in ESN, which enhances the connection among reser-voir states and increase the accuracy. Finally, Genetic Algorithm is applied to seek the most suitable parameters. The detecting ability of our proposed model is assessed on two kinds of distinct grammatical constructions data. It not only performs significantly better than the baselines in the meaning error and sentence error, but it also visualizes the expected probabilities for each of the possible thematic roles. (c) 2021 Elsevier B.V. All rights reserved.

Item Type: Article
Funders: Fundamental Research Funds for the Central Universities [3132019400] [3132021129]
Uncontrolled Keywords: Grammatical structure; Echo State Network; Instinct Plasticity; Weights selection; Genetic Algorithm
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology > Department of Artificial Intelligence
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 28 Apr 2022 07:51
Last Modified: 28 Apr 2022 07:51
URI: http://eprints.um.edu.my/id/eprint/33730

Actions (login required)

View Item View Item