Associative Self-Organizing Map
(2009) International Conference on Neural Computation (ICNC) 2009 p.363-370- Abstract
- We present a study of a novel variant of the Self-Organizing Map (SOM) called the Associative Self-Organizing Map (A-SOM). The A-SOM is similar to the SOM and thus develops a representation of its input space, but in addition it also learns to associate its activity with the activity of one or several external SOMs. The A-SOM has relevance in e.g. the modelling of expectations in one modality due to the activity invoked in another modality, and in the modelling of the neuroscientific simulation hypothesis. The paper presents the algorithm generalized to an arbitrary number of associated activities together with simulation results to find out about its performance and its ability to generalize to new inputs that it has not been trained on.... (More)
- We present a study of a novel variant of the Self-Organizing Map (SOM) called the Associative Self-Organizing Map (A-SOM). The A-SOM is similar to the SOM and thus develops a representation of its input space, but in addition it also learns to associate its activity with the activity of one or several external SOMs. The A-SOM has relevance in e.g. the modelling of expectations in one modality due to the activity invoked in another modality, and in the modelling of the neuroscientific simulation hypothesis. The paper presents the algorithm generalized to an arbitrary number of associated activities together with simulation results to find out about its performance and its ability to generalize to new inputs that it has not been trained on. The simulation results were very encouraging and confirmed the ability of the A-SOM to learn to associate the representations of its input space with the representations of the input spaces developed in two connected SOMs. Good generalization ability was also demonstrated. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1467770
- author
- Johnsson, Magnus LU ; Balkenius, Christian LU and Hesslow, Germund LU
- organization
- publishing date
- 2009
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Self-organizing map, Neural network, Associative self-Organizing map, A-SOM, SOM, ANN, Expectations, Simulation hypothesis, Cognitive modelling
- host publication
- IJCCI 2009: PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE
- pages
- 363 - 370
- publisher
- Institute for Systems and Technologies of Information, Control and Communication
- conference name
- International Conference on Neural Computation (ICNC) 2009
- conference location
- Madeira, Portugal
- conference dates
- 2009-10-05 - 2009-10-07
- external identifiers
-
- wos:000290915300053
- scopus:77955465677
- ISBN
- 978-989-674-014-6
- project
- Ikaros: An infrastructure for system level modelling of the brain
- Thinking in Time: Cognition, Communication and Learning
- language
- English
- LU publication?
- yes
- id
- 599698ae-bac6-46d0-be92-1431522ba6d2 (old id 1467770)
- date added to LUP
- 2016-04-04 10:08:19
- date last changed
- 2022-05-17 02:23:55
@inproceedings{599698ae-bac6-46d0-be92-1431522ba6d2, abstract = {{We present a study of a novel variant of the Self-Organizing Map (SOM) called the Associative Self-Organizing Map (A-SOM). The A-SOM is similar to the SOM and thus develops a representation of its input space, but in addition it also learns to associate its activity with the activity of one or several external SOMs. The A-SOM has relevance in e.g. the modelling of expectations in one modality due to the activity invoked in another modality, and in the modelling of the neuroscientific simulation hypothesis. The paper presents the algorithm generalized to an arbitrary number of associated activities together with simulation results to find out about its performance and its ability to generalize to new inputs that it has not been trained on. The simulation results were very encouraging and confirmed the ability of the A-SOM to learn to associate the representations of its input space with the representations of the input spaces developed in two connected SOMs. Good generalization ability was also demonstrated.}}, author = {{Johnsson, Magnus and Balkenius, Christian and Hesslow, Germund}}, booktitle = {{IJCCI 2009: PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE}}, isbn = {{978-989-674-014-6}}, keywords = {{Self-organizing map; Neural network; Associative self-Organizing map; A-SOM; SOM; ANN; Expectations; Simulation hypothesis; Cognitive modelling}}, language = {{eng}}, pages = {{363--370}}, publisher = {{Institute for Systems and Technologies of Information, Control and Communication}}, title = {{Associative Self-Organizing Map}}, year = {{2009}}, }