TY - GEN
T1 - Recurrent clustering for unsupervised feature extraction with application to sequence detection
AU - Young, Steven Robert
AU - Arel, Itamar
PY - 2012
Y1 - 2012
N2 - In many unsupervised learning applications both spatial and temporal regularities in the data need to be represented. Traditional clustering algorithms, which are commonly employed by unsupervised learning engines, lack the ability to naturally capture temporal dependencies. In supervised learning methods, temporal features are often learned through the use of a feedback (or recurrent) signal. Drawing inspiration from the Elman recurrent neural network, we introduce a winner-take-all based recurrent clustering algorithm that is able to identify temporal regularities in an unsupervised manner. We explore the potential pitfalls that result from adding feedback to an incremental clustering algorithm and apply the proposed technique to several time series inference problems in the context of semi-supervised learning. The results clearly indicate that the framework can be broadly applied with particular relevance to scalable deep machine learning architectures.
AB - In many unsupervised learning applications both spatial and temporal regularities in the data need to be represented. Traditional clustering algorithms, which are commonly employed by unsupervised learning engines, lack the ability to naturally capture temporal dependencies. In supervised learning methods, temporal features are often learned through the use of a feedback (or recurrent) signal. Drawing inspiration from the Elman recurrent neural network, we introduce a winner-take-all based recurrent clustering algorithm that is able to identify temporal regularities in an unsupervised manner. We explore the potential pitfalls that result from adding feedback to an incremental clustering algorithm and apply the proposed technique to several time series inference problems in the context of semi-supervised learning. The results clearly indicate that the framework can be broadly applied with particular relevance to scalable deep machine learning architectures.
KW - recurrent clustering
KW - semi-supervised learning
KW - spatiotemporal features
KW - time series analysis
UR - http://www.scopus.com/inward/record.url?scp=84873578628&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2012.140
DO - 10.1109/ICMLA.2012.140
M3 - Conference contribution
AN - SCOPUS:84873578628
SN - 9780769549132
T3 - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
SP - 54
EP - 55
BT - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
T2 - 11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012
Y2 - 12 December 2012 through 15 December 2012
ER -