On the optimization of Hierarchical Temporal Memory

Authors:
Ioannis Kostavelis;Antonios Gasteratos
Affiliations:
Laboratory of Robotics and Automation, Department of Production and Management Engineering, Democritus University of Thrace, Vasilissis Sophias 12, GR-671 00 Xanthi, Greece;Laboratory of Robotics and Automation, Department of Production and Management Engineering, Democritus University of Thrace, Vasilissis Sophias 12, GR-671 00 Xanthi, Greece
Venue:
Pattern Recognition Letters
Year:
2012

Citing 7
Cited 0

Disparity estimation on log-polar images and vergence control

Computer Vision and Image Understanding
Temporal Bayesian Network based contextual framework for structured information mining

Pattern Recognition Letters
A Study of the Different Uses of Colour Channels for Traffic Sign Recognition on Hierarchical Temporal Memory

ICICIC '09 Proceedings of the 2009 Fourth International Conference on Innovative Computing, Information and Control
Using hierarchical temporal memory for vision-based hand shape recognition under large variations in hand's rotation

ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Visual object-action recognition: Inferring object affordances from human demonstration

Computer Vision and Image Understanding
Optimizing hierarchical temporal memory for multivariable time series

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.10

Visualization

Abstract

In this paper an optimized classification method for object recognition is presented. The proposed method is based on the Hierarchical Temporal Memory (HTM), which stems from the memory prediction theory of the human brain. As in HTM, this method comprises a tree structure of connected computational nodes, whilst utilizing different rules to memorize objects appearing in various orientations. These rules involve both the spatial and the temporal module. As HTM is inspired from brain activity, its input should also comply with the human vision system. Thus, for the representation of the input images the logpolar was given preference to the Cartesian one. As compared to the original HTM method, experimental results exhibit performance enhancements with this approach, in recognition and categorization applications. Results obtained prove that the proposed method is more accurate and faster in training, whilst retaining the network robustness in multiple orientation variations.