---
abstract: 'Hierarchical Temporal Memory (HTM) is still largely unknown by the pattern recognition community and only a few studies have been published in the scientific literature. This paper reviews HTM architecture and related learning algorithms by using formal notation and pseudocode description. Novel approaches are then proposed to encode coincidence-group membership (fuzzy grouping) and to derive temporal groups (maxstab temporal clustering). Systematic experiments on three line-drawing datasets have been carried out to better understand HTM peculiarities and to extensively compare it against other well-know pattern recognition approaches. Our results prove the effectiveness of the new algorithms introduced and that HTM, even if still in its infancy, compares favorably with other existing technologies.'
altloc:
- http://bias.csr.unibo.it/maltoni/HTM_TR_v1.0.pdf
chapter: ~
commentary: ~
commref: ~
confdates: ~
conference: ~
confloc: ~
contact_email: ~
creators_id:
- davide.maltoni@unibo.it
creators_name:
- family: Maltoni
given: Davide
honourific: Prof.
lineage: ''
date: 2011-04-13
date_type: published
datestamp: 2014-02-25 12:49:04
department: DEIS
dir: disk0/00/00/91/87
edit_lock_since: ~
edit_lock_until: 0
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 9187
fileinfo: /style/images/fileicons/application_pdf.png;/9187/1/HTM_TR_v1.0.pdf
full_text_status: public
importid: ~
institution: University of Bologna
isbn: ~
ispublished: unpub
issn: ~
item_issues_comment: []
item_issues_count: ~
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: ~
lastmod: 2014-02-25 12:49:04
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: ~
pubdom: FALSE
publication: ~
publisher: ~
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 10
series: ~
source: ~
status_changed: 2014-02-25 12:49:04
subjects:
- comp-neuro-sci
- comp-sci-mach-vis
- comp-sci-neural-nets
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: Pattern Recognition by Hierarchical Temporal Memory
type: techreport
userid: 22383
volume: ~