TU Berlin

Fachgebiet NachrichtenübertragungEvolutionary Algorithm

Inhalt des Dokuments

zur Navigation

Hyper-Parameter Optimization for Convolutional Neural Networks Committees based on Evolutionary Algorithms

Lupe

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.

Publication:

Bochinski, E., Senst, T. and Sikora, T. HYPER-PARAMETER OPTIMIZATION FOR CONVOLUTIONAL NEURAL NETWORK COMMITTEES BASED ON EVOLUTIONARY ALGORITHMS. ICIP, 2017

 

 

 

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe