- Deep learning
-
Deep learning is a sub-field within machine learning that uses deep architectures to model complex relationships among data. Such models have proven to be effective feature extractors over high-dimensional, structured data (Hinton – Scholarpedia, 2009)[1].
One of the earliest successful implementations of a deep model (Hinton et al. 2006) involves learning the distribution of high level image (or possibly other data) features using successive layers of binary latent variables. However, real valued variables may also be used. The approach uses a restricted Boltzmann machine (Smolensky, 1986) to model each new layer of higher level features. Each new layer guarantees an increase on the lower-bound of the log likelihood of the data, thus improving the model, if trained properly. Once sufficiently many layers have been learned the deep architecture may be used as a generative model by reproducing the data when sampling down the model (an "ancestral pass") from the top level feature activations.
References
- Hinton, G. E.; Osindero, S.; Teh, Y. (2006). "A fast learning algorithm for deep belief nets". Neural Computation 18 (7): 1527–1554. doi:10.1162/neco.2006.18.7.1527. PMID 16764513. http://www.cs.toronto.edu/~hinton/absps/fastnc.pdf.
- Smolensky, P. (1986). Information processing in dynamical systems: Foundations of harmony theory.. 1. 194–281. http://portal.acm.org/citation.cfm?id=104290.
- ^ Scholarpedia: Deep Belief Networks - http://www.scholarpedia.org/article/Deep_belief_networks, 2009
External links
This article about a scientific organization is a stub. You can help Wikipedia by expanding it.
