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...
Asıl Yazarlar: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
Materyal Türü: | Journal article |
Dil: | English |
Baskı/Yayın Bilgisi: |
2006
|
Benzer Materyaller
-
Energy-based models for sparse overcomplete representations
Yazar:: Teh, Y, ve diğerleri
Baskı/Yayın Bilgisi: (2004) -
A fast learning algorithm for deep belief nets.
Yazar:: Hinton, G, ve diğerleri
Baskı/Yayın Bilgisi: (2006) -
Unsupervised part discovery from contrastive reconstruction
Yazar:: Choudhury, S, ve diğerleri
Baskı/Yayın Bilgisi: (2021) -
Backpropagation and the brain
Yazar:: Lillicrap, TP, ve diğerleri
Baskı/Yayın Bilgisi: (2020) -
Unsupervised discovery of parts, structure, and dynamics
Yazar:: Xu, Zhenjia, ve diğerleri
Baskı/Yayın Bilgisi: (2020)