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...
主要な著者: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
2006
|
類似資料
-
Energy-based models for sparse overcomplete representations
著者:: Teh, Y, 等
出版事項: (2004) -
A fast learning algorithm for deep belief nets.
著者:: Hinton, G, 等
出版事項: (2006) -
Unsupervised part discovery from contrastive reconstruction
著者:: Choudhury, S, 等
出版事項: (2021) -
Backpropagation and the brain
著者:: Lillicrap, TP, 等
出版事項: (2020) -
Unsupervised discovery of parts, structure, and dynamics
著者:: Xu, Zhenjia, 等
出版事項: (2020)