Improvement of the Backpropagation Algorithm Using (1+1) Evolutionary Strategies

Published in Book Chapters

  1. JoséParra Galaviz, Patricia Melin and Leonardo Trujillo. Improvement of the Backpropagation Algorithm Using (1+1) Evolutionary Strategies. In Patricia Melin, Janusz Kacprzyk and Witold Pedrycz (eds.). Soft Computing for Recognition Based on Biometrics. Studies in Computational Intelligence series, volume 312, Springer Berlin Heidelberg, 2010, pages 287-302. URL, DOI BibTeX

    	year = 2010,
    	isbn = "978-3-642-15110-1",
    	booktitle = "Soft Computing for Recognition Based on Biometrics",
    	volume = 312,
    	series = "Studies in Computational Intelligence",
    	editor = "Melin, Patricia and Kacprzyk, Janusz and Pedrycz, Witold",
    	doi = "10.1007/978-3-642-15111-8_18",
    	title = "Improvement of the Backpropagation Algorithm Using (1+1) Evolutionary Strategies",
    	url = "",
    	publisher = "Springer Berlin Heidelberg",
    	author = "Galaviz, JoséParra and Melin, Patricia and Trujillo, Leonardo",
    	pages = "287-302"


Currently, the standard in supervised Artificial Neural Networks (ANNs) research is to use the backpropagation (BP) algorithm or one of its improved variants, for training. In this chapter, we present an improvement to the most widely used BP learning algorithm using (1+1) evolutionary Strategy (ES), one of the most widely used artificial evolution paradigms. The goal is to provide a method that can adaptively change the main learning parameters of the BP algorithm in an unconstrained manner. The BP/ES algorithm we propose is simple to implement and can be used in combination with various improved versions of BP. In our experimental tests we can see a substantial improvement in ANN performance, in some cases a reduction of more than 50% in error for time series prediction on a standard benchmark test. Therefore, we believe that our proposal effectively combines the learning abilities of BP with the global search of ES to provide a useful tool that improves the quality of learning for BP-based methods.

Published in
Soft Computing for Recognition Based on Biometrics
Studies in Computational Intelligence
Pages 287-302
Chapter 10
Volume 312
Log in