//
<<
Details
Conference/Proceedings24th IEEE International Conference on Image Processing (ICIP)
Start date17.09.2017
End date20.09.2017
AddressBeijing, China
Pages3924-2928
Author(s)Erik Bochinski, Tobias Senst, Thomas Sikora
TitleHyper-Parameter Optimization for Convolutional Neural Network Committees Based on Evolutionary Algorithms
AbstractIn 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.
Key wordsmultimedia analysis, Image Classification, Convolutional Neural Network, Evolutionary Algorithm, MNIST, Hyper-parameter Optimization
NoteISBN: 978-1-5090-2174-1
File1507Bochinski2017.pdf

BibTeX