Large search spaces as those of artificial neural networks are difficult to search with machine learning techniques. The large amount of parameters is the main challenge for search techniques that do not exploit correlations expressed as patterns in the parameter space. Evolutionary computation with indirect genotype-phenotype mapping was proposed as a possible solution, but current methods often fail when the space is fractured and presents irregularities. This study employs an evolutionary indirect encoding inspired by developmental biology. Cellular proliferations and deletions of variable size allow for the definition of both regular large areas and small detailed areas in the parameter space. The method is tested on the search of the weights of a neural network for the classification of the MNIST dataset. The results demonstrate that even large networks such as those required for image classification can be effectively automatically designed by the proposed evolutionary developmental method. The combination of real-world problems like vision and classification, evolution and development, endows the proposed method with aspects of particular relevance to artificial life.
Funding
This work was supported by the Polish National Science
Center (project BIOMERGE, 2011/03/B/ST6/00399). This
work was also partially supported by the European Communitys
Seventh Framework Programme FP7/2007-2013,
Challenge 2 Cognitive Systems, Interaction, Robotics under
grant agreement No 248311 - AMARSi.
History
School
Science
Department
Computer Science
Published in
Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE XIV). Cambridge, MA: MIT Press, 2014
Pages
1 - 8
Citation
FONTANA, A., SOLTOGGIO, A. and WROBEL, B., 2014. POET: an evo-devo method to optimize the weights of a large artificial neural networks. IN: Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE XIV). Cambridge, MA: MIT Press, pp. 447-454.
Publisher
MIT Press
Version
VoR (Version of Record)
Publisher statement
This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/