The Community for Technology Leaders
Neural Networks, IEEE - INNS - ENNS International Joint Conference on (2009)
Atlanta, Ga, USA
June 14, 2009 to June 19, 2009
ISBN: 978-1-4244-3548-7
pp: 3032-3037
Douglas P. Sutton , United States Air Force Academy, Colorado Springs, 80840, USA
Martin C. Carlisle , United States Air Force Academy, Colorado Springs, 80840, USA
Traci A. Sarmiento , United States Air Force Academy, Colorado Springs, 80840, USA
Leemon C. Baird , United States Air Force Academy, Colorado Springs, 80840, USA
ABSTRACT
A new method is given for speeding up learning in a deep neural network with many hidden layers, by partially partitioning the network rather than fully interconnecting the layers. Empirical results are shown both for learning a simple Boolean function on a standard backprop network, and for learning two different, complex, real-world vision tasks on a more sophisticated convolutional network. In all cases, the performance of the proposed system was better than traditional systems. The partially-partitioned network outperformed both the fully-partitioned and fully-unpartitioned networks.
INDEX TERMS
CITATION

T. A. Sarmiento, L. C. Baird, D. P. Sutton and M. C. Carlisle, "Partitioned neural networks," Neural Networks, IEEE - INNS - ENNS International Joint Conference on(IJCNN), Atlanta, Ga, USA, 2009, pp. 3032-3037.
doi:10.1109/IJCNN.2009.5178994
93 ms
(Ver 3.3 (11022016))