Associative Arithmetic with Boltzmann Machines: The Role of Number Representations
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
The rate adapting poisson model for information retrieval and object recognition
ICML '06 Proceedings of the 23rd international conference on Machine learning
Dynamic hierarchical Markov random fields and their application to web data extraction
Proceedings of the 24th international conference on Machine learning
Training restricted Boltzmann machines using approximations to the likelihood gradient
Proceedings of the 25th international conference on Machine learning
Dynamic Hierarchical Markov Random Fields for Integrated Web Data Extraction
The Journal of Machine Learning Research
Using fast weights to improve persistent contrastive divergence
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Social influence analysis in large-scale networks
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
A new dual wing harmonium model for document retrieval
Pattern Recognition
A multiclass classification method based on decoding of binary classifiers
Neural Computation
A novel dual wing harmonium model aided by 2-D wavelet transform subbands for document data mining
Expert Systems with Applications: An International Journal
Unsupervised Layer-Wise Model Selection in Deep Neural Networks
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Neural decoding with hierarchical generative models
Neural Computation
A connection between score matching and denoising autoencoders
Neural Computation
Conditional graphical models for protein structure prediction
Conditional graphical models for protein structure prediction
Learning algorithms for the classification restricted Boltzmann machine
The Journal of Machine Learning Research
Hi-index | 0.00 |
We present a new learning algorithm for Mean Field Boltzmann Machines based on the contrastive divergence optimization criterion. In addition to minimizing the divergence between the data distribution and the equilibrium distribution, we maximize the divergence between one-step reconstructions of the data and the equilibrium distribution. This eliminates the need to estimate equilibrium statistics, so we do not need to approximate the multimodal probability distribution of the free network with the unimodal mean field distribution. We test the learning algorithm on the classification of digits.