Deep spatiotemporal feature learning with application to image classification

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

Deep machine learning is an emerging framework for dealing with complex high-dimensionality data in a hierarchical fashion which draws some inspiration from biological sources. Despite the notable progress made in the field, there remains a need for an architecture that can represent temporal information with the same ease that spatial information is discovered. In this work, we present new results using a recently introduced deep learning architecture called Deep Spatio-Temporal Inference Network (DeSTIN). DeSTIN is a discriminative deep learning architecture that combines concepts from unsupervised learning for dynamic pattern representation together with Bayesian inference. In DeSTIN the spatiotemporal dependencies that exist within the observations are modeled inherently in an unguided manner. Each node models the inputs by means of clustering and simple dynamics modeling while it constructs a belief state over the distribution of sequences using Bayesian inference. We demonstrate that information from the different layers of this hierarchical system can be extracted and utilized for the purpose of pattern classification. Earlier simulation results indicated that the framework is highly promising, consequently in this work we expand DeSTIN to a popular problem, the MNIST data set of handwritten digits. The system as a preprocessor to a neural network achieves a recognition accuracy of 97.98% on this data set. We further show related experimental results pertaining to automatic cluster adaptation and termination.

Original languageEnglish
Title of host publicationProceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010
Pages883-888
Number of pages6
DOIs
StatePublished - 2010
Event9th International Conference on Machine Learning and Applications, ICMLA 2010 - Washington, DC, United States
Duration: Dec 12 2010Dec 14 2010

Publication series

NameProceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010

Conference

Conference9th International Conference on Machine Learning and Applications, ICMLA 2010
Country/TerritoryUnited States
CityWashington, DC
Period12/12/1012/14/10

Keywords

  • Biologically-inspired computing
  • Deep learning
  • Online clustering

Fingerprint

Dive into the research topics of 'Deep spatiotemporal feature learning with application to image classification'. Together they form a unique fingerprint.

Cite this