computer science Computer science is the study of computation, automation, and information. Computer science spans theoretical disciplines (such as algorithms, theory of computation, information theory, and automation) to practical disciplines (includin ...

, a convolutional deep belief network (CDBN) is a type of

deep Deep or The Deep may refer to: Places United States * Deep Creek (Appomattox River tributary), Virginia * Deep Creek (Great Salt Lake), Idaho and Utah * Deep Creek (Mahantango Creek tributary), Pennsylvania * Deep Creek (Mojave River tributary), ...

artificial neural network Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural networks that constitute animal brains. An ANN is based on a collection of connected units ...

composed of multiple layers of convolutional

restricted Boltzmann machine A restricted Boltzmann machine (RBM) is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs. RBMs were initially invented under the name Harmonium by Paul Smolensky in 1986, and ros ...

s stacked together. Alternatively, it is a hierarchical

generative model In statistical classification, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is incons ...

for deep learning, which is highly effective in

image processing An image is a visual representation of something. It can be two-dimensional, three-dimensional, or somehow otherwise feed into the visual system to convey information. An image can be an artifact, such as a photograph or other two-dimension ...

and

object recognition Object recognition – technology in the field of computer vision for finding and identifying objects in an image or video sequence. Humans recognize a multitude of objects in images with little effort, despite the fact that the image of the ...

, though it has been used in other domains too. The salient features of the model include the fact that it scales well to high-dimensional images and is translation-invariant.{{cite web, last=Coviello, first=Emanuele, title=Convolutional Deep Belief Networks, url=http://cseweb.ucsd.edu/~dasgupta/254-deep/emanuele.pdf CDBNs use the technique of probabilistic max-pooling to reduce the dimensions in higher layers in the network. Training of the network involves a pre-training stage accomplished in a greedy layer-wise manner, similar to other

deep belief network In machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a class of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not be ...

s. Depending on whether the network is to be used for discrimination or generative tasks, it is then "fine tuned" or trained with either

back-propagation In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...

or the up–down algorithm (contrastive–divergence), respectively.

References

Artificial neural networks Probabilistic models