Hierarchical Temporal Memory for Behavior Prediction

Visa enkel post
dc.contributor.authorBjörkman, David
dc.contributor.departmentChalmers tekniska högskola / Institutionen för tillämpad informationsteknologi (Chalmers)sv
dc.contributor.departmentChalmers University of Technology / Department of Applied Information Technology (Chalmers)en
dc.date.accessioned2019-07-03T12:59:44Z
dc.date.available2019-07-03T12:59:44Z
dc.date.issued2012
dc.description.abstractThis thesis is about researching and analyzing Hierarchical Temporal Memory, specifically the newly developed "HTM Cortical learning algorithms"[3] developed by Jeff Hawkins and the company Numenta. Two problems are addressed. Can this type of hierarchical memory system make an internal representation of simple data sequences at the input? And if so, does it take long to learn? Two C++ applications were developed in this thesis. The first program is used to analyze the algorithm, and the second program is used to visualize the internal states of the network. The results is very dependent of how the system is configured. If enough resources are available, the system can learn sequences, and it does not take long for the system to learn.
dc.identifier.urihttps://hdl.handle.net/20.500.12380/163276
dc.language.isoeng
dc.relation.ispartofseriesReport - IT University of Göteborg, Chalmers University of Technology and the University of Göteborg
dc.setspec.uppsokHumanitiesTheology
dc.subjectMänniska-datorinteraktion (interaktionsdesign)
dc.subjectInformations- och kommunikationsteknik
dc.subjectHuman Computer Interaction
dc.subjectInformation & Communication Technology
dc.titleHierarchical Temporal Memory for Behavior Prediction
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster Thesisen
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
163276.pdf
Storlek:
753.35 KB
Format:
Adobe Portable Document Format
Beskrivning:
Fulltext
Ladda ner
Samling
Examensarbeten för masterexamen