Abstract
Hierarchical temporal memory~(HTM) is an emerging machine learning algorithm, with the potential to provide a means to perform predictions on spatiotemporal data. The algorithm, inspired by the neocortex, currently does not have a comprehensive mathematical framework. This work brings together all aspects of the spatial pooler~(SP), a critical learning component in HTM, under a single unifying framework. The primary learning mechanism is explored, where a maximum likelihood estimator for determining the degree of permanence update is proposed. The boosting mechanisms are studied and found to be a secondary learning mechanism. The SP is demonstrated in both spatial and categorical multi-class classification, where the SP is found to perform exceptionally well on categorical data. Observations are made relating HTM to well-known algorithms such as competitive learning and attribute bagging. Methods are provided for using the SP for classification as well as dimensionality reduction. Empirical evidence verifies that given the proper parameterizations, the SP may be used for feature learning.
Highlights
Hierarchical temporal memory (HTM), created by Hawkins and George (2007), is a machine learning algorithm that was inspired by the neocortex and designed to learn sequences and make predictions
A mathematical framework for HTM’s spatial pooler (SP) was presented. It was demonstrated how the SP can be used for feature learning
It was shown that the mechanism consists of two distinct components, permanence selection and the degree of permanence update
Summary
Hierarchical temporal memory (HTM), created by Hawkins and George (2007), is a machine learning algorithm that was inspired by the neocortex and designed to learn sequences and make predictions. Given time-series data, HTM should be able to use its learned representations to perform a type of time-dependent regression. Such a system would prove to be incredibly useful in many applications utilizing spatiotemporal data. HTM’s prominence in the machine learning community has been hampered, largely due to the evolving nature of HTM’s algorithmic definition and the lack of a formalized mathematical model. This work aims to bridge the gap between a neuroscience inspired algorithm and a math-based algorithm by constructing a purely mathematical framework around HTM’s original algorithmic definition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
