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...
Autors principals: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
Format: | Journal article |
Idioma: | English |
Publicat: |
2006
|
Ítems similars
-
Energy-based models for sparse overcomplete representations
per: Teh, Y, et al.
Publicat: (2004) -
A fast learning algorithm for deep belief nets.
per: Hinton, G, et al.
Publicat: (2006) -
Unsupervised part discovery from contrastive reconstruction
per: Choudhury, S, et al.
Publicat: (2021) -
Backpropagation and the brain
per: Lillicrap, TP, et al.
Publicat: (2020) -
Unsupervised discovery of parts, structure, and dynamics
per: Xu, Zhenjia, et al.
Publicat: (2020)