Convolutional deep belief network
In computer science, Convolutional Deep Belief Network (CDBN) is a type of deep neural network that is composed of multiple layers of convolutional restricted Boltzmann machines stacked together.[1] Alternatively, it is a hierarchical generative model for deep learning, which is highly effective in the tasks of image processing and object recognition, though it has been used in other domains too.[2] The salient features of the model include the fact that it scales well to high dimensional images and is translation-invariant.[3]
CDBNs use the technique of probabilistic max-pooling to reduce the dimensions in higher layers in the network. Training of the network is accomplished in a greedy layer-wise manner, similar to other deep learning networks.
References
- ^ Lee, Honglak. "Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations" (PDF).
{{cite journal}}: Cite journal requires|journal=(help); Unknown parameter|coauthors=ignored (|author=suggested) (help) - ^ Lee, Honglak. "Unsupervised feature learning for audio classification using convolutional deep belief networks" (PDF).
{{cite web}}: Unknown parameter|coauthors=ignored (|author=suggested) (help) - ^ Coviello, Emanuele. "Convolutional Deep Belief Networks" (PDF).
 | This article has not been added to any content categories. Please help out by adding categories to it so that it can be listed with similar articles. (April 2014) |