Asynchronous Evolution of Convolutional Networks

Authors: Petra Vidnerová, Roman Neruda
Publication year: 2018
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: ITAT 2018: Information Technologies – Applications and Theory. Proceedings of the 18th conference ITAT 2018
Projects: Capabilities and limitations of shallow and deep networks
Bibliographic citation: VIDNEROVÁ, Petra, NERUDA, Roman. Asynchronous Evolution of Convolutional Networks. In: KRAJČI, S., ed. ITAT 2018: Information Technologies – Applications and Theory. Proceedings of the 18th conference ITAT 2018. Aachen: Technical University & CreateSpace Independent Publishing Platform, 2018, S. 80-85. CEUR Workshop Proceedings, V-2203. ISSN 1613-0073. Dostupné z: http://ceur-ws.org/Vol-2203/80.pdf
ID: 494108
Online record: View online record

Abstract

Due to many successful practical applications, deep neural networks and convolutional networks have become the state-of-art machine learning methods recently. The choice of network architecture for the task at hand is typically made by trial and error. This work deals with an automatic data-dependent architecture design. We propose an algorithm for optimization of architecture of convolutional network based on asynchronous evolution. The algorithm is inspired by and designed directly for the Keras library which is one of the most common implementations of deep neural networks. The proposed algorithm is successfully tested on MNIST and Fashion-MNIST data sets.