A fast learning algorithm for deep belief nets.
We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one l...
Main Authors: | Hinton, G, Osindero, S, Teh, Y |
---|---|
Format: | Journal article |
Language: | English |
Published: |
2006
|
Similar Items
-
Unsupervised discovery of nonlinear structure using contrastive backpropagation.
by: Hinton, G, et al.
Published: (2006) -
Energy-based models for sparse overcomplete representations
by: Teh, Y, et al.
Published: (2004) -
A tutorial on stochastic approximation algorithms for training Restricted Boltzmann Machines and Deep Belief Nets
by: Swersky, K, et al.
Published: (2010) -
SemNet: Learning semantic attributes for human activity recognition with deep belief networks
by: Shanmuga Venkatachalam, et al.
Published: (2022-08-01) -
Corrigendum: SemNet: Learning semantic attributes for human activity recognition with deep belief networks
by: Shanmuga Venkatachalam, et al.
Published: (2023-03-01)