Extending Hierarchical Temporal Memory for Sequence Classification

Klaus Greff
Mastersthesis, Technische Universität Kaiserslautern, 2010.


This thesis tackles the problem of sequence learning using Hierarchical Temporal Memory as a first step towards a framework for combined temoral and spatial inference. Hierarchical Temporal Memory (HTM) is a quite new technology (2008) inspired by the human cortex to do (spatial) classification. In this thesis, we extend the theoretical framework of HTMs enabling them to do sequence classification. The improved framework is implemented and used to evaluate the algorithms on artificial data. We show this approach to be a viable first step towards a joint inference.

Weitere Links