Transformation equivariant Boltzmann machines

Authors:
Jyri J. Kivinen;Christopher K. I. Williams
Affiliations:
Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, UK;Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, UK
Venue:
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Year:
2011

Citing 8
Cited 0

Lending direction to neural networks

Neural Networks
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A fast learning algorithm for deep belief nets

Neural Computation
Learning to segment images using dynamic feature binding

Neural Computation
Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Learning to represent spatial transformations with factored higher-order boltzmann machines

Neural Computation
Image Modeling and Denoising With Orientation-Adapted Gaussian Scale Mixtures

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We develop a novel modeling framework for Boltzmann machines, augmenting each hidden unit with a latent transformation assignment variable which describes the selection of the transformed view of the canonical connection weights associated with the unit. This enables the inferences of the model to transform in response to transformed input data in a stable and predictable way, and avoids learning multiple features differing only with respect to the set of transformations. Extending prior work on translation equivariant (convolutional) models, we develop translation and rotation equivariant restricted Boltzmann machines (RBMs) and deep belief nets (DBNs), and demonstrate their effectiveness in learning frequently occurring statistical structure from artificial and natural images.