Information processing in dynamical systems: foundations of harmony theory
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning and relearning in Boltzmann machines
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Original Contribution: Stacked generalization
Neural Networks
Machine Learning
Bias/variance decompositions for likelihood-based estimators
Neural Computation
Genetic Programming and Evolvable Machines
Analysis of errors of handwritten digits made by a multitude of classifiers
Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld
A fast learning algorithm for deep belief nets
Neural Computation
Connectionist computations of intuitionistic reasoning
Theoretical Computer Science
Gabor wavelet similarity maps for optimising hierarchical road sign classifiers
Pattern Recognition Letters
Introducing a very large dataset of handwritten Farsi digits and a study on their varieties
Pattern Recognition Letters
Deformation Models for Image Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A hierarchical approach to recognition of handwritten Bangla characters
Pattern Recognition
What kind of a graphical model is the brain?
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Building a multi-FPGA virtualized restricted boltzmann machine architecture using embedded MPI
Proceedings of the 19th ACM/SIGDA international symposium on Field programmable gate arrays
SIP'06 Proceedings of the 5th WSEAS international conference on Signal processing
Handwritten digit recognition using low rank approximation based competitive neural network
ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
| Hi-index | 0.15 |
The product of experts learning procedurecan discover a set of stochastic binary features that constitute a nonlinear generative model of handwritten images of digits. The quality of generative models learned in this way can be assessed by learning a separate model for each class of digit and then comparing the unnormalized probabilities of test images under the 10 different class-specific models. To improve discriminative performance, a hierarchy of separate models can be learned for each digit class. Each model in the hierarchy learns a layer of binary feature detectors that model the probability distribution of vectors of activity of feature detectors in the layer below. The models in the hierarchy are trained sequentially and each model uses a layer of binary feature detectors to learn a generative model of the patterns of feature activities in the preceding layer. After training, each layer of feature dectectors produces a separate, unnormalized log probabilty score. With three layers of feature detectors for each of the 10 digit classes, a test image produces 30 scores which can be used as inputs to a supervised, logistic classification network that is trained on separate data. On the MNIST database, our system is comparable with current state-of-the-art discriminative methods, demonstrating that the product of experts learning procedure can produce effective hierarchies of generative models of high-dimensional data.