kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Neural Network based Explicit Mixture Models and Expectation-maximization based Learning
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-0394-1087
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0002-0737-2531
KTH, School of Electrical Engineering and Computer Science (EECS), Centres, ACCESS Linnaeus Centre. KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-2638-6047
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0001-7182-9543
2020 (English)In: Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc. , 2020Conference paper, Published paper (Refereed)
Abstract [en]

We propose two neural network based mixture models in this work. The proposed mixture models are explicit. The explicit models have analytical forms with the advantages of computing likelihood and efficiency of generating samples. Expectation-maximization based algorithms are developed for learning parameters of the proposed models. We provide sufficient conditions to realize the expectation-maximization based learning. The main requirements are invertibility of neural networks that are used as generators and Jacobian computation of functional form of the neural networks. The requirements are practically realized using a flow-based neural network. In our first mixture model, we use multiple flow-based neural networks as generators. Naturally the model is complex. A single latent variable is used as the common input to all the neural networks. The second mixture model uses a single flow-based neural network as a generator to reduce complexity. The single generator has a latent variable input that follows a Gaussian mixture distribution. The proposed models are verified via training with expectation-maximization based algorithms on practical datasets. We demonstrate efficiency of proposed mixture models through extensive experiments for generating samples and maximum likelihood based classification.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2020.
Keywords [en]
classification, expectation maximization, Generative model, mixture models, neural network, Complex networks, Efficiency, Learning systems, Maximum likelihood, Maximum principle, Analytical forms, Expectation - maximizations, Explicit models, Functional forms, Gaussian mixture distribution, Generating samples, Latent variable, Learning parameters, Neural networks
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:kth:diva-291297DOI: 10.1109/IJCNN48605.2020.9207086ISI: 000626021403121Scopus ID: 2-s2.0-85093853732OAI: oai:DiVA.org:kth-291297DiVA, id: diva2:1538888
Conference
2020 International Joint Conference on Neural Networks, IJCNN 2020, 19 July 2020 through 24 July 2020
Note

QC 20210322QC 20210721

Available from: 2021-03-22 Created: 2021-03-22 Last updated: 2023-04-03Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Liu, DongVu, Minh ThànhChatterjee, SaikatRasmussen, Lars Kildehöj

Search in DiVA

By author/editor
Liu, DongVu, Minh ThànhChatterjee, SaikatRasmussen, Lars Kildehöj
By organisation
Information Science and EngineeringACCESS Linnaeus Centre
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 32 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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