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...
मुख्य लेखकों: | Hinton, G, Osindero, S, Welling, M, Teh, Y |
---|---|
स्वरूप: | Journal article |
भाषा: | English |
प्रकाशित: |
2006
|
समान संसाधन
-
Energy-based models for sparse overcomplete representations
द्वारा: Teh, Y, और अन्य
प्रकाशित: (2004) -
A fast learning algorithm for deep belief nets.
द्वारा: Hinton, G, और अन्य
प्रकाशित: (2006) -
Unsupervised part discovery from contrastive reconstruction
द्वारा: Choudhury, S, और अन्य
प्रकाशित: (2021) -
Backpropagation and the brain
द्वारा: Lillicrap, TP, और अन्य
प्रकाशित: (2020) -
Unsupervised discovery of parts, structure, and dynamics
द्वारा: Xu, Zhenjia, और अन्य
प्रकाशित: (2020)