Change search
ReferencesLink to record
Permanent link

Direct link
Pattern Recognition with Vector Symbolic Architectures
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
2016 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Pattern recognition is an area constantly enlarging its theoretical and practical horizons. Applications of pattern recognition and machine learning can be found in many areas of the present day world including health-care, robotics, manufacturing, economics, automation, transportation, etc. Despite some success in many domains pattern recognition algorithms are still far from being close to their biological vis-a-vis – human brain. New possibilities in the area of pattern recognition may be achieved by application of biologically inspired approaches. This thesis presents the usage of a bio-inspired method of representing concepts and their meaning – Vector Symbolic Architectures – in the context of pattern recognition with possible applications in intelligent transportation systems, automation systems, and language processing. Vector Symbolic Architectures is an approach for encoding and manipulating distributed representations of information. They have previously been used mainly in the area of cognitive computing for representing and reasoning upon semantically bound information. First, it is shown that Vector Symbolic Architectures are capable of pattern classification of temporal patterns. With this approach, it is possible to represent, learn and subsequently classify vehicles using measurements from vibration sensors.Next, an architecture called Holographic Graph Neuron for one-shot learning of patterns of generic sensor stimuli is proposed. The architecture is based on implementing the Hierarchical Graph Neuron approach using Vector Symbolic Architectures. Holographic Graph Neuron shows the previously reported performance characteristics of Hierarchical Graph Neuron while maintaining the simplicity of its design. The Holographic Graph Neuron architecture is applied in two domains: fault detection and longest common substrings search. In the area of fault detection the architecture showed superior performance compared to classical methods of artificial intelligence while featuring zero configuration and simple operations. The application of the architecture for longest common substrings search showed its ability to robustly solve the task given that the length of a common substring is longer than 4% of the longest pattern. Furthermore, the required number of operations on binary vectors is equal to the suffix trees approach, which is the fastest traditional algorithm for this problem. In summary, the work presented in this thesis extends understanding of the performance proprieties of distributed representations and opens the way for new applications.

Place, publisher, year, edition, pages
Luleå tekniska universitet, 2016. , 136 p.
Series
Licentiate thesis / Luleå University of Technology, ISSN 1402-1757
Research subject
Dependable Communication and Computation Systems
Identifiers
URN: urn:nbn:se:ltu:diva-17439Local ID: 367cffae-c4a6-451f-81ce-10d2e520681aISBN: 978-91-7583-535-8ISBN: 978-91-7583-536-5 (PDF)OAI: oai:DiVA.org:ltu-17439DiVA: diva2:990444
Note
Godkänd; 2016; 20160207 (denkle); Nedanstående person kommer att hålla licentiatseminarium för avläggande av teknologie licentiatexamen. Namn: Denis Kleyko Ämne: Kommunikations- och beräkningssystem / Dependable Communication and Computation Systems Uppsats: Pattern Recognition with Vector Symbolic Architectures Examinator: Professor Evgeny Osipov Institutionen för system- och rymdteknik, Avdelning: Datavetenskap, Luleå tekniska universitet. Diskutant: Associate Professor Okko Räsänen, Aalto University, Department of Signal Processing and Acoustics, Finland. Tid: Måndag 21 mars, 2016 kl 10.00 Plats: A109, Luleå tekniska universitetAvailable from: 2016-09-29 Created: 2016-09-29Bibliographically approved

Open Access in DiVA

fulltext(5088 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 5088 kBChecksum SHA-512
26bacda4d5be1e387f8b30dd56cc9e2a7f708602ddb126af0bbf95adce7605c42d18867e421dcffdda0969f87de336b366e1bf82b47cdc2ba6a383e33ce0bdf6
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Kleyko, Denis
By organisation
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 24 hits
ReferencesLink to record
Permanent link

Direct link