Computer Science – Learning
Scientific paper
2012-02-14
Computer Science
Learning
Scientific paper
Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not applicable to conditional models and there has been almost no work on training and generating predictions from conditional RBMs for structured output problems. We first argue that standard Contrastive Divergence-based learning may not be suitable for training CRBMs. We then identify two distinct types of structured output prediction problems and propose an improved learning algorithm for each. The first problem type is one where the output space has arbitrary structure but the set of likely output configurations is relatively small, such as in multi-label classification. The second problem is one where the output space is arbitrarily structured but where the output space variability is much greater, such as in image denoising or pixel labeling. We show that the new learning algorithms can work much better than Contrastive Divergence on both types of problems.
Hinton Geoffrey E.
Larochelle Hugo
Mnih Volodymyr
No associations
LandOfFree
Conditional Restricted Boltzmann Machines for Structured Output Prediction does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Conditional Restricted Boltzmann Machines for Structured Output Prediction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Conditional Restricted Boltzmann Machines for Structured Output Prediction will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-90609