Backpropagation learning with a (1+1) ES

Published in Conferences Papers
  1. Leonardo Trujillo, Pierrick Legrand, Gustavo Olague and Cynthia Pérez. Optimization of the HöLder Image Descriptor Using a Genetic Algorithm. In Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation. 2010, 1147–1154. URL, DOI BibTeX

    @inproceedings{Trujillo:2010:OHI:1830483.1830695,
    	author = "Trujillo, Leonardo and Legrand, Pierrick and Olague, Gustavo and P{\'e}rez, Cynthia",
    	title = {Optimization of the H\"{o}Lder Image Descriptor Using a Genetic Algorithm},
    	booktitle = "Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation",
    	series = "GECCO '10",
    	year = 2010,
    	isbn = "978-1-4503-0072-8",
    	location = "Portland, Oregon, USA",
    	pages = "1147--1154",
    	numpages = 8,
    	url = "http://doi.acm.org/10.1145/1830483.1830695",
    	doi = "10.1145/1830483.1830695",
    	acmid = 1830695,
    	publisher = "ACM",
    	address = "New York, NY, USA",
    	keywords = "genetic algorithms, h?lderian regularity, image descriptors"
    }
    
Abstract

We present an improvement to backpropagation (BP) learning for neural networks using a (1+1) evolutionary strategy (ES). The goal is to provide a method than can adaptively change the learning parameters used in BP in an unconstrained manner. The BP/ES algorithm we propose is simple to implement and can be used with various versions of BP. In our experiments there is a substantial increase in performance for time series prediction

Published in
GECCO '10 Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Pages 2103-2104
http://dl.acm.org/citation.cfm?id=1830883
Date of conference
07 - 11 July 2010
ISBN
978-1-4503-0073-5
Feedback