neural networks research group
areas
people
projects
demos
publications
software/data
Temporal Convolution Machines for Sequence Learning (2009)
Alan J Lockett
and
Risto Miikkulainen
The Temporal Convolution Machine (TCM) is a neural architecture for learning temporal sequences that generalizes the Temporal Restricted Boltzmann Machine (TRBM). A convolution function is used to provide a trainable envelope of time sensitivity in the bias terms. Gaussian and multi-Gaussian envelopes with trainable means and variances are evaluated as particular instances of the TCM architecture. First, Gaussian and multi-Gaussian TCMs are shown to learn a class of multi-modal distributions over synthetic binary spatiotemporal data better than comparable TRBM models. Second, these networks are trained to recall digitized versions of baroque sonatas. In this task, a multi-Gaussian TCM performs effective sequence mapping when the input sequence is partially hidden. The TCM is therefore a promising approach to learning more complex temporal data than was previously possible.
View:
PDF
Citation:
Technical Report AI-09-04, Department of Computer Sciences, the University of Texas at Austin, 2009.
Bibtex:
@techreport{lockett:aitr09-04, title={Temporal Convolution Machines for Sequence Learning}, author={Alan J Lockett and Risto Miikkulainen}, number={AI-09-04}, institution={Department of Computer Sciences, the University of Texas at Austin}, url="http://nn.cs.utexas.edu/?lockett:aitr09-04", year={2009} }
People
Alan J. Lockett
Ph.D. Alumni
alan lockett [at] gmail com
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Projects
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Areas of Interest
Supervised Learning
Unsupervised Learning, Clustering, and Self-Organization
Applications