IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization

Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization
View Sample PDF
Author(s): Swathi Jamjala Narayanan (VIT University, India), Boominathan Perumal (VIT University, India) and Jayant G. Rohra (VIT University, India)
Copyright: 2018
Pages: 31
Source title: Handbook of Research on Modeling, Analysis, and Application of Nature-Inspired Metaheuristic Algorithms
Source Author(s)/Editor(s): Sujata Dash (North Orissa University, India), B.K. Tripathy (VIT University, India) and Atta ur Rahman (University of Dammam, Saudi Arabia)
DOI: 10.4018/978-1-5225-2857-9.ch002

Purchase

View Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization on the publisher's website for pricing and purchasing information.

Abstract

Nature-inspired algorithms have been productively applied to train neural network architectures. There exist other mechanisms like gradient descent, second order methods, Levenberg-Marquardt methods etc. to optimize the parameters of neural networks. Compared to gradient-based methods, nature-inspired algorithms are found to be less sensitive towards the initial weights set and also it is less likely to become trapped in local optima. Despite these benefits, some nature-inspired algorithms also suffer from stagnation when applied to neural networks. The other challenge when applying nature inspired techniques for neural networks would be in handling large dimensional and correlated weight space. Hence, there arises a need for scalable nature inspired algorithms for high dimensional neural network optimization. In this chapter, the characteristics of nature inspired techniques towards optimizing neural network architectures along with its applicability, advantages and limitations/challenges are studied.

Related Content

Ying Tan. © 2020. 41 pages.
JunQi Zhang, JianQing Chen, WeiZhi Li. © 2020. 13 pages.
Jun Yu, Hideyuki Takagi. © 2020. 15 pages.
Daniel C. Lee, Katherine Manson. © 2020. 37 pages.
Sreeja N. K.. © 2020. 21 pages.
Shoufei Han, Kun Zhu. © 2020. 18 pages.
Yu Xue. © 2020. 28 pages.
Body Bottom