Unsupervised discovery of nonlinear structure using contrastive backpropagation.
We describe a way of modeling high-dimensional data vectors by using an unsupervised, nonlinear, multilayer neural network in which the activity of each neuron-like unit makes an additive contribution to a global energy score that indicates how surprised the network is by the data vector. The connec...
Autores principales: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
Formato: | Journal article |
Lenguaje: | English |
Publicado: |
2006
|
Ejemplares similares
-
Energy-based models for sparse overcomplete representations
por: Teh, Y, et al.
Publicado: (2004) -
A fast learning algorithm for deep belief nets.
por: Hinton, G, et al.
Publicado: (2006) -
Unsupervised part discovery from contrastive reconstruction
por: Choudhury, S, et al.
Publicado: (2021) -
Backpropagation and the brain
por: Lillicrap, TP, et al.
Publicado: (2020) -
Unsupervised discovery of parts, structure, and dynamics
por: Xu, Zhenjia, et al.
Publicado: (2020)