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...
Prif Awduron: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
Fformat: | Journal article |
Iaith: | English |
Cyhoeddwyd: |
2006
|
Eitemau Tebyg
-
Energy-based models for sparse overcomplete representations
gan: Teh, Y, et al.
Cyhoeddwyd: (2004) -
A fast learning algorithm for deep belief nets.
gan: Hinton, G, et al.
Cyhoeddwyd: (2006) -
Unsupervised part discovery from contrastive reconstruction
gan: Choudhury, S, et al.
Cyhoeddwyd: (2021) -
Backpropagation and the brain
gan: Lillicrap, TP, et al.
Cyhoeddwyd: (2020) -
Unsupervised discovery of parts, structure, and dynamics
gan: Xu, Zhenjia, et al.
Cyhoeddwyd: (2020)