Gated boltzmann machine in texture modeling

Authors:
Tele Hao;Tapani Raiko;Alexander Ilin;Juha Karhunen
Affiliations:
Department of Information and Computer Science, Aalto University, Espoo, Finland;Department of Information and Computer Science, Aalto University, Espoo, Finland;Department of Information and Computer Science, Aalto University, Espoo, Finland;Department of Information and Computer Science, Aalto University, Espoo, Finland
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 8
Cited 0

Class-Specific Material Categorisation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
A Statistical Approach to Material Classification Using Image Patch Exemplars

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning to represent spatial transformations with factored higher-order boltzmann machines

Neural Computation
Deep, big, simple neural nets for handwritten digit recognition

Neural Computation
Improved learning of Gaussian-Bernoulli restricted Boltzmann machines

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Texture Classification from Random Features

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we consider the problem of modeling complex texture information using undirected probabilistic graphical models. Texture is a special type of data that one can better understand by considering its local structure. For that purpose, we propose a convolutional variant of the Gaussian gated Boltzmann machine (GGBM) [12], inspired by the co-occurrence matrix in traditional texture analysis. We also link the proposed model to a much simpler Gaussian restricted Boltzmann machine where convolutional features are computed as a preprocessing step. The usefulness of the model is illustrated in texture classification and reconstruction experiments.