Dynamic object recognition using sparse coded three-way conditional restricted Boltzmann machines

Dynamic object recognition using sparse coded three-way conditional restricted Boltzmann machines

Zhao, W.
Bou Ammar, H.
Roos, N.

2013-11-08

In this paper a novel framework capable of both accurate predictions and classifications of dynamic images is introduced. The proposed technique makes of use of a novel combination of sparse coding, a feature extraction algorithm, and three-way weight tensor conditional restricted Boltzmann machines, a form of deep learning. Experiments performed on both the prediction and classification of various images show the efficiency, accuracy, and effectiveness of the proposed technique.

http://resolver.tudelft.nl/uuid:0509dc93-f168-4181-aeea-64241a15be02

Conference proceedings

conference paper

(c) 2013 Zhao, W.; Bou Ammar, H.; Roos, N.