Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Vector Symbolic Architectures and their applications: Computing with random vectors in a hyperdimensional space
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.ORCID iD: 0000-0002-6032-6155
2018 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Vektor symboliska Arkitekturer och deras tillämpningar : Beräkning med slumpmässiga vektorer i ett hyperdimensionellt utrymme (Swedish)
Abstract [en]

The main focus of this thesis lies in a rather narrow subfield of Artificial Intelligence. As any beloved child, it has many names. The most common ones are Vector Symbolic Architectures and Hyperdimensional Computing. Vector Symbolic Architectures are a family of bio-inspired methods of representing and manipulating concepts and their meanings in a high-dimensional space (hence Hyperdimensional Computing). Information in Vector Symbolic Architectures is evenly distributed across representational units, therefore, it is said that they operate with distributed representations. Representational units can be of different nature, however, the thesis concentrates on the case when units have either binary or integer values. 

This thesis includes eleven scientific papers and extends the research area in three directions: theory of Vector Symbolic Architectures, their applications for pattern recognition, and unification of Vector Symbolic Architectures with other neural-like computational approaches. 

Previously, Vector Symbolic Architectures have been used mainly in the area of cognitive computing for representing and reasoning upon semantically bound information, for example, for analogy-based reasoning. This thesis significantly extends the applicability of Vector Symbolic Architectures to an area of pattern recognition. Pattern recognition is the 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 the success in many domains pattern recognition algorithms are still far from being close to their biological vis-a-vis – the brain. In particular, one of the challenges is a large amount of training data required by conventional machine learning algorithms. Therefore, it is important to look for new possibilities in the area via exploring biologically inspired approaches.

All application scenarios, which are considered in the thesis, contribute to the development of the global strategy of creating an information society. Specifically, such important applications as biomedical signal processing, automation systems, and text processing were considered. All applications scenarios used novel methods of mapping data to Vector Symbolic Architectures proposed in the thesis.

In the domain of biomedical signal processing, Vector Symbolic Architectures were applied for three tasks: classification of a modality of medical images, gesture recognition, and assessment of synchronization of cardiovascular signals. In the domain of automation systems, Vector Symbolic Architectures were used for a data-driven fault isolation. In the domain of text processing, Vector Symbolic Architectures were used to search for the longest common substring and to recognize permuted words.

The theoretical contributions of the thesis come in four aspects. First, the thesis proposes several methods for mapping data from its original representation into a distributed representation suitable for further manipulations by Vector Symbolic Architectures. These methods can be used for one-shot learning of patterns of generic sensor stimuli. Second, the thesis presents the analysis of an informational capacity of Vector Symbolic Architectures in the case of binary distributed representations. Third, it is shown how to represent finite state automata using Vector Symbolic Architectures. Fourth, the thesis describes the approach of combining Vector Symbolic Architectures and a cellular automaton.

Finally, the thesis presents the results of unification of two computational approaches with Vector Symbolic Architectures. This is one of the most interesting cross-disciplinary contributions of the thesis. First, it is shown that Bloom Filters – an important data structure for an approximate membership query task – can be treated in terms of Vector Symbolic Architectures. It allows generalizing the process of building the filter. Second, Vector Symbolic Architectures and Echo State Networks (a special kind of recurrent neural networks) were combined together. It is possible to implement Echo State Networks using only integer values in network’s units and much simpler operation for a recurrency operation while preserving the entire dynamics of the network. It results in a simpler architecture with lower requirements on memory and operations. 

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2018.
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering Computer Systems Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
URN: urn:nbn:se:ltu:diva-68338ISBN: 978-91-7790-110-5 (print)ISBN: 978-91-7790-111-2 (electronic)OAI: oai:DiVA.org:ltu-68338DiVA, id: diva2:1197565
Public defence
2018-06-11, A109, Luleå, 10:00 (English)
Opponent
Supervisors
Funder
Swedish Research Council, 2015-04677Available from: 2018-04-16 Created: 2018-04-13 Last updated: 2018-05-31Bibliographically approved
List of papers
1. Modality Classification of Medical Images with Distributed Representations Based on Cellular Automata Reservoir Computing
Open this publication in new window or tab >>Modality Classification of Medical Images with Distributed Representations Based on Cellular Automata Reservoir Computing
2017 (English)In: Proceedings - International Symposium on Biomedical Imaging, Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 1053-1056Conference paper, Published paper (Refereed)
Abstract [en]

Modality corresponding to medical images is a vital filter in medical image retrieval systems. This article presents the classification of modalities of medical images based on the usage of principles of hyper-dimensional computing and reservoir computing. It is demonstrated that the highest classification accuracy of the proposed method is on a par with the best classical method for the given dataset (83% vs. 84%). The major positive property of the proposed method is that it does not require any optimization routine during the training phase and naturally allows for incremental learning upon the availability of new training data.

Place, publisher, year, edition, pages
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2017
Series
Proceedings. IEEE International Symposium on Biomedical Imaging, E-ISSN 1945-7928
National Category
Medical Image Processing Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-61558 (URN)10.1109/ISBI.2017.7950697 (DOI)000414283200243 ()2-s2.0-85023198723 (Scopus ID)9781509011711 (ISBN)
Conference
2017 IEEE International Symposium on Biomedical Imaging, Melbourne, Australia, 18-21 April 2017
Funder
Swedish Research Council, 2015-04677
Available from: 2017-01-20 Created: 2017-01-20 Last updated: 2018-07-10Bibliographically approved
2. No Two Brains Are Alike: Cloning a Hyperdimensional Associative Memory Using Cellular Automata Computations
Open this publication in new window or tab >>No Two Brains Are Alike: Cloning a Hyperdimensional Associative Memory Using Cellular Automata Computations
2017 (English)In: Biologically Inspired Cognitive Architectures (BICA) for Young Scientists: First International Early Research Career Enhancement School on BICA and Cybersecurity (FIERCES 2017) / [ed] Alexei V. Samsonovich, Valentin V. Klimov, Cham: Springer, 2017, p. 91-100Conference paper, Published paper (Refereed)
Abstract [en]

This paper looks beyond of the current focus of research on biologically inspired cognitive systems and considers the problem of replication of its learned functionality. The considered challenge is to replicate the learned knowledge such that uniqueness of the internal symbolic representations is guaranteed. This article takes a neurological argument “no two brains are alike” and suggests an architecture for mapping a content of the trained associative memory built using principles of hyperdimensional computing and Vector Symbolic Architectures into a new and orthogonal basis of atomic symbols. This is done with the help of computations on cellular automata. The results of this article open a way towards a secure usage of cognitive architectures in a variety of practical application domains.

Place, publisher, year, edition, pages
Cham: Springer, 2017
Series
Advances in Intelligent Systems and Computing, ISSN 2194-5357 ; 636
National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-63644 (URN)10.1007/978-3-319-63940-6_13 (DOI)000454681600013 ()978-3-319-63939-0 (ISBN)978-3-319-63940-6 (ISBN)
Conference
First International Early Research Career Enhancement School on BICA and Cybersecurity (FIERCES 2017), Moscow, Russia, 1-6 August 2017
Funder
Swedish Research Council
Available from: 2017-06-01 Created: 2017-06-01 Last updated: 2019-01-29Bibliographically approved
3. On bidirectional transitions between localist and distributed representations: The case of common substrings search using Vector Symbolic Architecture
Open this publication in new window or tab >>On bidirectional transitions between localist and distributed representations: The case of common substrings search using Vector Symbolic Architecture
2014 (English)In: Procedia Computer Science, ISSN 1877-0509, E-ISSN 1877-0509, Vol. 41, p. 104-113Article in journal (Refereed) Published
Abstract [en]

The contribution of this article is twofold. First, it presents an encoding approach for seamless bidirectional transitions between localist and distributed representation domains. Second, the approach is demonstrated on the example of using Vector Symbolic Architecture for solving a problem of finding common substrings. The proposed algorithm uses elementary operations on long binary vectors. For the case of two patterns with respective lengths L1 and L2 it requires Θ(L1 + L2 – 1) operations on binary vectors, which is equal to the suffix trees approach – the fastest algorithm for this problem. The simulation results show that in order to be robustly detected by the proposed approach the length of a common substring should be more than 4% of the longest pattern.

National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-15592 (URN)10.1016/j.procs.2014.11.091 (DOI)000361488600014 ()f200757d-c493-4d45-af4f-2c61f85a73e8 (Local ID)f200757d-c493-4d45-af4f-2c61f85a73e8 (Archive number)f200757d-c493-4d45-af4f-2c61f85a73e8 (OAI)
Conference
International Conference on Biologically Inspired Cognitive Architectures : Fifth Annual Meeting of the BICA Society 07/11/2014 - 09/11/2014
Note
Validerad; 2015; Nivå 2; 20140824 (denkle)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
4. Recognizing permuted words with Vector Symbolic Architectures: A Cambridge test for machines
Open this publication in new window or tab >>Recognizing permuted words with Vector Symbolic Architectures: A Cambridge test for machines
2016 (English)In: Procedia Computer Science, ISSN 1877-0509, E-ISSN 1877-0509, Vol. 88, p. 169-175Article in journal (Refereed) Published
Abstract [en]

This paper proposes a simple encoding scheme for words using principles of Vector Symbolic Architectures. The proposed encoding allows finding a valid word in the dictionary for a given permuted word (represented using the proposed approach) using only a single operation - calculation of Hamming distance to the distributed representations of valid words in the dictionary. The proposed encoding scheme can be used as an additional processing mechanism for models of word embedding, which also form vectors to represent the meanings of words, in order to match the distorted words in the text to the valid words in the dictionary.

National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-40430 (URN)10.1016/j.procs.2016.07.421 (DOI)000391723200024 ()f921c1ad-944a-4427-88f6-7559bdb89676 (Local ID)f921c1ad-944a-4427-88f6-7559bdb89676 (Archive number)f921c1ad-944a-4427-88f6-7559bdb89676 (OAI)
Conference
7th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2016, July 16-19 2016 in New York City
Note

2017-03-27 (andbra);Konferensartikel i tidskrift

Available from: 2016-10-03 Created: 2016-10-03 Last updated: 2018-07-10Bibliographically approved
5. Fault Detection in the Hyperspace: Towards Intelligent Automation Systems
Open this publication in new window or tab >>Fault Detection in the Hyperspace: Towards Intelligent Automation Systems
Show others...
2015 (English)In: IEEE International Conference on Industrial Informatics: INDIN 2015, Cambridge, UK, July 22-24, 2015. Proceedings, Piscataway, NJ: IEEE Communications Society, 2015, p. 1219-1224, article id 7281909Conference paper, Published paper (Refereed)
Abstract [en]

This article presents a methodology for intelligent, biologically inspired fault detection system for generic complex systems of systems. The proposed methodology utilizes the concepts of associative memory and vector symbolic architectures, commonly used for modeling cognitive abilities of human brain. Compared to classical methods of artificial intelligence used in the context of fault detection the proposed methodology shows an unprecedented performance, while featuring zero configuration and simple operations.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2015
National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-32046 (URN)10.1109/INDIN.2015.7281909 (DOI)2-s2.0-84949512219 (Scopus ID)668a6fde-3e94-4870-a560-0ea6e83a5245 (Local ID)9781479966493 (ISBN)668a6fde-3e94-4870-a560-0ea6e83a5245 (Archive number)668a6fde-3e94-4870-a560-0ea6e83a5245 (OAI)
Conference
IEEE International Conference on Industrial Informatics : 22/07/2015 - 24/07/2015
Note
Validerad; 2016; Nivå 1; 20150522 (denkle)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2018-07-10Bibliographically approved
6. Holographic Graph Neuron: a Bio-Inspired Architecture for Pattern Processing
Open this publication in new window or tab >>Holographic Graph Neuron: a Bio-Inspired Architecture for Pattern Processing
Show others...
2017 (English)In: IEEE Transactions on Neural Networks and Learning Systems, ISSN 2162-237X, E-ISSN 2162-2388, Vol. 28, no 6, p. 1250-1262Article in journal (Refereed) Published
Abstract [en]

This article proposes the use of Vector Symbolic Architectures for implementing Hierarchical Graph Neuron, an architecture for memorizing patterns of generic sensor stimuli. The adoption of a Vector Symbolic representation ensures a one-layered design for the approach, while maintaining the previously reported properties and performance characteristics of Hierarchical Graph Neuron, and also improving the noise resistance of the architecture. The proposed architecture enables a linear (with respect to the number of stored entries) time search for an arbitrary sub-pattern.

Place, publisher, year, edition, pages
IEEE, 2017
National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-11974 (URN)10.1109/TNNLS.2016.2535338 (DOI)000401982100001 ()26978836 (PubMedID)2-s2.0-84960540059 (Scopus ID)b0709bbc-d372-4032-90cc-1dca4ff3a12d (Local ID)b0709bbc-d372-4032-90cc-1dca4ff3a12d (Archive number)b0709bbc-d372-4032-90cc-1dca4ff3a12d (OAI)
Note

Validerad;2017;Nivå 2;2017-06-01 (andbra)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
7. Classification and Recall With Binary Hyperdimensional Computing: Tradeoffs in Choice of Density and Mapping Characteristics
Open this publication in new window or tab >>Classification and Recall With Binary Hyperdimensional Computing: Tradeoffs in Choice of Density and Mapping Characteristics
Show others...
2018 (English)In: IEEE Transactions on Neural Networks and Learning Systems, ISSN 2162-237X, E-ISSN 2162-2388, Vol. 29, no 12, p. 5880-5898Article in journal (Refereed) Published
Abstract [en]

Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic appliances operating at low power. This paper discusses tradeoffs of selecting parameters of binary HD representations when applied to pattern recognition tasks. Particular design choices include density of representations and strategies for mapping data from the original representation. It is demonstrated that for the considered pattern recognition tasks (using synthetic and real-world data) both sparse and dense representations behave nearly identically. This paper also discusses implementation peculiarities which may favor one type of representations over the other. Finally, the capacity of representations of various densities is discussed.

Place, publisher, year, edition, pages
IEEE, 2018
National Category
Computer Systems
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-68400 (URN)10.1109/TNNLS.2018.2814400 (DOI)000451230100008 ()29993669 (PubMedID)2-s2.0-85045214003 (Scopus ID)
Funder
Swedish Research Council, 2015- 04677
Note

Validerad;2018;Nivå 2;2018-12-05 (svasva)

Available from: 2018-04-18 Created: 2018-04-18 Last updated: 2019-03-04Bibliographically approved
8. Associative Synthesis of Finite State Automata Model of a Controlled Object with Hyperdimensional Computing
Open this publication in new window or tab >>Associative Synthesis of Finite State Automata Model of a Controlled Object with Hyperdimensional Computing
2017 (English)In: Proceedings IECON 2017: 43rd Annual Conference of the IEEE Industrial Electronics Society, Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 3276-3281Conference paper, Published paper (Refereed)
Abstract [en]

The main contribution of this paper is a study of the applicability of hyperdimensional computing and learning with an associative memory for modeling the dynamics of complex automation systems. Specifically, the problem of learning an evidence-based model of a plant in a distributed automation and control system is considered. The model is learned in the form a finite state automata. 

Place, publisher, year, edition, pages
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2017
Series
IEEE Industrial Electronics Society, ISSN 1553-572X
National Category
Computer Systems
Research subject
Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-66594 (URN)10.1109/IECON.2017.8216554 (DOI)000427164803042 ()2-s2.0-85046676612 (Scopus ID)9781538611272 (ISBN)
Conference
43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017, Bejing, China, 29 October - 1 November 2017
Available from: 2017-11-16 Created: 2017-11-16 Last updated: 2018-05-21Bibliographically approved

Open Access in DiVA

fulltext(21137 kB)481 downloads
File information
File name FULLTEXT01.pdfFile size 21137 kBChecksum SHA-512
a77655bb9897f99fc85bbb503932e8d67586c552368c62bf58761c1a47b2784b5b8d808fafef4dc2bce35e72438d022d1de71bbd7c666dcc51b8be2c0f14f744
Type fulltextMimetype application/pdf

Authority records BETA

Kleyko, Denis

Search in DiVA

By author/editor
Kleyko, Denis
By organisation
Computer Science
Other Electrical Engineering, Electronic Engineering, Information EngineeringComputer SystemsComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 481 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

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 4011 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf