Predictions Tasks with Words and Sequences: Comparing a Novel Recurrent Architecture with the Elman Network
(2011) International Joint Conference on Neural Networks (IJCNN) 2011 p.1207-1213- Abstract
- The classical connectionist models are not well suited to working with data varying over time. According to this, temporal connectionist models have emerged and constitute a continuously growing research field. In this paper we present a novel supervised recurrent neural network architecture (SARASOM) based on the Associative Self-Organizing Map (A-SOM). The A-SOM is a variant of the Self-Organizing Map (SOM) that develops a representation of its input space as well as learns to associate its activity with an arbitrary number of additional inputs. In this context the A-SOM learns to associate its previous activity with a delay of one iteration. The performance of the SARASOM was evaluated and compared with the Elman network in a number of... (More)
- The classical connectionist models are not well suited to working with data varying over time. According to this, temporal connectionist models have emerged and constitute a continuously growing research field. In this paper we present a novel supervised recurrent neural network architecture (SARASOM) based on the Associative Self-Organizing Map (A-SOM). The A-SOM is a variant of the Self-Organizing Map (SOM) that develops a representation of its input space as well as learns to associate its activity with an arbitrary number of additional inputs. In this context the A-SOM learns to associate its previous activity with a delay of one iteration. The performance of the SARASOM was evaluated and compared with the Elman network in a number of prediction tasks using sequences of letters (including some experiments with a reduced lexicon of 10 words). The results are very encouraging with SARASOM learning slightly better than the Elman network. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1982547
- author
- Gil, David LU ; Garcia, J ; Cazorla, M and Johnsson, Magnus LU
- organization
- publishing date
- 2011
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- [Host publication title missing]
- pages
- 1207 - 1213
- conference name
- International Joint Conference on Neural Networks (IJCNN) 2011
- conference location
- San Jose, California, United States
- conference dates
- 2011-07-31 - 2011-08-05
- external identifiers
-
- scopus:80054746210
- ISSN
- 2161-4393
- ISBN
- 978-1-4244-9635-8
- DOI
- 10.1109/IJCNN.2011.6033361
- project
- Thinking in Time: Cognition, Communication and Learning
- language
- English
- LU publication?
- yes
- id
- e2c253d5-d93e-4e6e-92a6-253d8fa7740c (old id 1982547)
- date added to LUP
- 2016-04-04 09:22:11
- date last changed
- 2022-01-29 17:33:03
@inproceedings{e2c253d5-d93e-4e6e-92a6-253d8fa7740c, abstract = {{The classical connectionist models are not well suited to working with data varying over time. According to this, temporal connectionist models have emerged and constitute a continuously growing research field. In this paper we present a novel supervised recurrent neural network architecture (SARASOM) based on the Associative Self-Organizing Map (A-SOM). The A-SOM is a variant of the Self-Organizing Map (SOM) that develops a representation of its input space as well as learns to associate its activity with an arbitrary number of additional inputs. In this context the A-SOM learns to associate its previous activity with a delay of one iteration. The performance of the SARASOM was evaluated and compared with the Elman network in a number of prediction tasks using sequences of letters (including some experiments with a reduced lexicon of 10 words). The results are very encouraging with SARASOM learning slightly better than the Elman network.}}, author = {{Gil, David and Garcia, J and Cazorla, M and Johnsson, Magnus}}, booktitle = {{[Host publication title missing]}}, isbn = {{978-1-4244-9635-8}}, issn = {{2161-4393}}, language = {{eng}}, pages = {{1207--1213}}, title = {{Predictions Tasks with Words and Sequences: Comparing a Novel Recurrent Architecture with the Elman Network}}, url = {{http://dx.doi.org/10.1109/IJCNN.2011.6033361}}, doi = {{10.1109/IJCNN.2011.6033361}}, year = {{2011}}, }