Welcome to the InfoSci Platform
Reference Hub1
Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization

Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization

Swathi Jamjala Narayanan, Boominathan Perumal, Jayant G. Rohra
Copyright: © 2018 |Pages: 31
ISBN13: 9781522528579|ISBN10: 1522528571|EISBN13: 9781522528586
DOI: 10.4018/978-1-5225-2857-9.ch002
Cite Chapter Cite Chapter

MLA

Narayanan, Swathi Jamjala, et al. "Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization." Handbook of Research on Modeling, Analysis, and Application of Nature-Inspired Metaheuristic Algorithms, edited by Sujata Dash, et al., IGI Global, 2018, pp. 23-53. https://doi.org/10.4018/978-1-5225-2857-9.ch002

APA

Narayanan, S. J., Perumal, B., & Rohra, J. G. (2018). Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization. In S. Dash, B. Tripathy, & A. Rahman (Eds.), Handbook of Research on Modeling, Analysis, and Application of Nature-Inspired Metaheuristic Algorithms (pp. 23-53). IGI Global. https://doi.org/10.4018/978-1-5225-2857-9.ch002

Chicago

Narayanan, Swathi Jamjala, Boominathan Perumal, and Jayant G. Rohra. "Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization." In Handbook of Research on Modeling, Analysis, and Application of Nature-Inspired Metaheuristic Algorithms, edited by Sujata Dash, B.K. Tripathy, and Atta ur Rahman, 23-53. Hershey, PA: IGI Global, 2018. https://doi.org/10.4018/978-1-5225-2857-9.ch002

Export Reference

Mendeley
Favorite

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.