A Cognitive Model for Generalization during Sequential Learning
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 principle...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2011-01-01
|
Series: | Journal of Robotics |
Online Access: | http://dx.doi.org/10.1155/2011/617613 |
Summary: | 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. |
---|---|
ISSN: | 1687-9600 1687-9619 |