direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Scientific Publications

Hyper-Parameter Optimization for Convolutional Neural Network Committees Based on Evolutionary Algorithms
Citation key 1507Bochinski2017
Author Erik Bochinski and Tobias Senst and Thomas Sikora
Title of Book 24th IEEE International Conference on Image Processing (ICIP)
Pages 3924–2928
Year 2017
Address Beijing, China
Month sep
Note ISBN: 978-1-5090-2174-1
Abstract In a broad range of computer vision tasks, convolutional neural networks (CNNs) are one of the most prominent techniques due to their outstanding performance. Yet it is not trivial to find the best performing network structure for a specific application because it is often unclear how the network structure relates to the network accuracy. We propose an evolutionary algorithm-based framework to automatically optimize the CNN structure by means of hyper-parameters. Further, we extend our framework towards a joint optimization of a committee of CNNs to leverage specialization and cooperation among the individual networks. Experimental results show a significant improvement over the state-of-the-art on the well-established MNIST dataset for hand-written digits recognition.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe