TY - GEN
T1 - Deep spatiotemporal feature learning with application to image classification
AU - Karnowski, Thomas P.
AU - Arel, Itamar
AU - Rose, Derek
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
KW - Biologically-inspired computing
KW - Deep learning
KW - Online clustering
UR - http://www.scopus.com/inward/record.url?scp=79952390246&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2010.138
DO - 10.1109/ICMLA.2010.138
M3 - Conference contribution
AN - SCOPUS:79952390246
SN - 9780769543000
T3 - Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010
SP - 883
EP - 888
BT - Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010
T2 - 9th International Conference on Machine Learning and Applications, ICMLA 2010
Y2 - 12 December 2010 through 14 December 2010
ER -