Learning Deep Structured Models
Preprint
Abstract
Many problems in real-world applications involve predicting several random variables which are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such relationships. The goal of this paper is to combine MRFs with deep learning algorithms to estimate complex representations while taking into account the dependencies between the output random variables. Towards this goal, we propose a training algorithm that is able to learn structured models jointly with deep features that form the MRF potentials. Our approach is efficient as it blends learning and inference and makes use of GPU acceleration. We demonstrate the effectiveness of our algorithm in the tasks of predicting words from noisy images, as well as multi-class classification of Flickr photographs. We show that joint learning of the deep features and the MRF parameters results in significant performance gains.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- An Efficient Learning Procedure for Deep Boltzmann MachinesNeural Computation, 2012
- A conditional neural fields model for protein threadingBioinformatics, 2012
- Backpropagation training for multilayer conditional random field based phone recognition2010
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations2009
- Conditional Random Fields for Integrating Local Discriminative ClassifiersIEEE Transactions on Audio, Speech, and Language Processing, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Constructing Free-Energy Approximations and Generalized Belief Propagation AlgorithmsIEEE Transactions on Information Theory, 2005
- A New Class of Upper Bounds on the Log Partition FunctionIEEE Transactions on Information Theory, 2005
- Global training of document processing systems using graph transformer networks2002
- Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference.The Journal of Philosophy, 1991