Advanced

Internal Simulation of Perceptions and Actions

Johnsson, Magnus LU and Gil, David LU (2011) In From Brains to Systems: Brain-Inspired Cognitive Systems 2010 718. p.87-100
Abstract
We present a study of neural network architectures able to internally simulate perceptions and actions. All these architectures employ the novel Associative Self-Organizing Map (A-SOM) as a perceptual neural network. The A-SOM develops a representation of its input space, but in addition also learns to associate its activity with an arbitrary number of additional (possibly delayed) inputs. One architecture is a bimodal perceptual architecture whereas the others include an action neural network adapted by the delta rule. All but one architecture are recurrently connected. We have tested the architectures with very encouraging simulation results. The bimodal perceptual architecture was able to simulate appropriate sequences of activity... (More)
We present a study of neural network architectures able to internally simulate perceptions and actions. All these architectures employ the novel Associative Self-Organizing Map (A-SOM) as a perceptual neural network. The A-SOM develops a representation of its input space, but in addition also learns to associate its activity with an arbitrary number of additional (possibly delayed) inputs. One architecture is a bimodal perceptual architecture whereas the others include an action neural network adapted by the delta rule. All but one architecture are recurrently connected. We have tested the architectures with very encouraging simulation results. The bimodal perceptual architecture was able to simulate appropriate sequences of activity patterns in the absence of sensory input for several epochs in both modalities. The architecture without recurrent connections correctly classified 100% of the training samples and 80% of the test samples. After ceasing to receive any input the best of the architectures with recurrent connections was able to continue to produce 100% correct output sequences for 28 epochs (280 iterations), and then to continue with 90% correct output sequences until epoch 42. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
From Brains to Systems: Brain-Inspired Cognitive Systems 2010
volume
718
pages
87 - 100
publisher
Springer
external identifiers
  • WOS:000293603200008
  • Scopus:83455259384
ISSN
0065-2598
ISBN
978-1-4614-0163-6
DOI
10.1007/978-1-4614-0164-3_8
project
Cognition, Communication and Learning
language
English
LU publication?
yes
id
ad36f678-dab6-40f8-82f1-3b2abf90bfd1 (old id 1982544)
date added to LUP
2011-09-20 11:23:58
date last changed
2017-01-01 06:05:16
@inbook{ad36f678-dab6-40f8-82f1-3b2abf90bfd1,
  abstract     = {We present a study of neural network architectures able to internally simulate perceptions and actions. All these architectures employ the novel Associative Self-Organizing Map (A-SOM) as a perceptual neural network. The A-SOM develops a representation of its input space, but in addition also learns to associate its activity with an arbitrary number of additional (possibly delayed) inputs. One architecture is a bimodal perceptual architecture whereas the others include an action neural network adapted by the delta rule. All but one architecture are recurrently connected. We have tested the architectures with very encouraging simulation results. The bimodal perceptual architecture was able to simulate appropriate sequences of activity patterns in the absence of sensory input for several epochs in both modalities. The architecture without recurrent connections correctly classified 100% of the training samples and 80% of the test samples. After ceasing to receive any input the best of the architectures with recurrent connections was able to continue to produce 100% correct output sequences for 28 epochs (280 iterations), and then to continue with 90% correct output sequences until epoch 42.},
  author       = {Johnsson, Magnus and Gil, David},
  isbn         = {978-1-4614-0163-6},
  issn         = {0065-2598},
  language     = {eng},
  pages        = {87--100},
  publisher    = {Springer},
  series       = {From Brains to Systems: Brain-Inspired Cognitive Systems 2010},
  title        = {Internal Simulation of Perceptions and Actions},
  url          = {http://dx.doi.org/10.1007/978-1-4614-0164-3_8},
  volume       = {718},
  year         = {2011},
}