A Cognitive Model for Generalization during Sequential Learning
Joint Authors
Vig, Lovekesh
Noelle, David C.
Gupta, Ashish
Source
Issue
Vol. 2011, Issue 2011 (31 Dec. 2011), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2011-12-28
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
Traditional artificial neural network models of learning suffer from catastrophic interference.
They are commonly trained to perform only one specific task, and, when trained on a new task, they forget the original task completely.
It has been shown that the foundational neurocomputational principles embodied by the Leabra cognitive modeling framework, specifically fast lateral inhibition and a local synaptic plasticity model that incorporates both correlational and error-based components, are sufficient to largely overcome this limitation during the sequential learning of multiple motor skills.
Evidence has also provided that Leabra is able to generalize the subsequences of motor skills, when doing so is appropriate.
In this paper, we provide a detailed analysis of the extent of generalization possible with Leabra during sequential learning of multiple tasks.
For comparison, we measure the generalization exhibited by the backpropagation of error learning algorithm.
Furthermore, we demonstrate the applicability of sequential learning to a pair of movement tasks using a simulated robotic arm.
American Psychological Association (APA)
Gupta, Ashish& Vig, Lovekesh& Noelle, David C.. 2011. A Cognitive Model for Generalization during Sequential Learning. Journal of Robotics،Vol. 2011, no. 2011, pp.1-12.
https://search.emarefa.net/detail/BIM-485517
Modern Language Association (MLA)
Gupta, Ashish…[et al.]. A Cognitive Model for Generalization during Sequential Learning. Journal of Robotics No. 2011 (2011), pp.1-12.
https://search.emarefa.net/detail/BIM-485517
American Medical Association (AMA)
Gupta, Ashish& Vig, Lovekesh& Noelle, David C.. A Cognitive Model for Generalization during Sequential Learning. Journal of Robotics. 2011. Vol. 2011, no. 2011, pp.1-12.
https://search.emarefa.net/detail/BIM-485517
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-485517