Neural Network Approaches for Perception and Action

Ritter H (1997)
In: Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings. Sommer G, Koenderink JJ (Eds); Lecture Notes in Computer Science 1315, 1315. Berlin: Springer: 356-378.

Conference Paper | Published | English

No fulltext has been uploaded

Editor
Sommer, Gerald ; Koenderink, Jan J.
Abstract
We argue that endowing machines with perception and action raises many problems for which solutions derived from first principles are unfeasable or too costly and that artificial neural networks offer a worthwhile and natural approach towards a solution. As a result, learning methods for creating mappings or dynamical systems that implement a desired functionality replace the implementation of algorithms by programming. We discuss two neural network approaches, the Local Linear Maps (LLMs) and the Parametrized Self-Organizing Maps (PSOMs), that are well suited for the rapid construction of mapping modules and illustrate some of their possibilies with examples from robot vision and manipulator control. We also address some more general issues, such as the need for mechanisms of attention control and for the flexible association of continuous degrees of freedom, together with an ability for handling varying constraints during the selection of actions.
Publishing Year
Conference
AFPAC'97
Location
Kiel
Conference Date
1997-09-08 – 1997-09-09
PUB-ID

Cite this

Ritter H. Neural Network Approaches for Perception and Action. In: Sommer G, Koenderink JJ, eds. Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings. Lecture Notes in Computer Science 1315. Vol 1315. Berlin: Springer; 1997: 356-378.
Ritter, H. (1997). Neural Network Approaches for Perception and Action. In G. Sommer & J. J. Koenderink (Eds.), Lecture Notes in Computer Science 1315: Vol. 1315. Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings (pp. 356-378). Berlin: Springer.
Ritter, H. (1997). “Neural Network Approaches for Perception and Action” in Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings, ed. G. Sommer and J. J. Koenderink Lecture Notes in Computer Science 1315, vol. 1315, (Berlin: Springer), 356-378.
Ritter, H., 1997. Neural Network Approaches for Perception and Action. In G. Sommer & J. J. Koenderink, eds. Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings. Lecture Notes in Computer Science 1315. no.1315 Berlin: Springer, pp. 356-378.
H. Ritter, “Neural Network Approaches for Perception and Action”, Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings, G. Sommer and J.J. Koenderink, eds., Lecture Notes in Computer Science 1315, vol. 1315, Berlin: Springer, 1997, pp.356-378.
Ritter, H.: Neural Network Approaches for Perception and Action. In: Sommer, G. and Koenderink, J.J. (eds.) Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings. Lecture Notes in Computer Science 1315. 1315, p. 356-378. Springer, Berlin (1997).
Ritter, Helge. “Neural Network Approaches for Perception and Action”. Algebraic Frames for the Perception-Action Cycle: International Workshop, AFPAC'97 Kiel, Germany, September 8–9, 1997 Proceedings. Ed. Gerald Sommer and Jan J. Koenderink. Berlin: Springer, 1997.Vol. 1315. Lecture Notes in Computer Science 1315. 356-378.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search