Riassunto
Questo capitolo illustra i principi alla base dell’apprendimento dei robot e delle macchine e ne esamina i meccanismi più comunemente usati, quali l’apprendimento per rinforzo e gli approcci connessionistici. Presenta inoltre tre casi di studio di robot che possiedono la capacità di imparare.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
4.5 Letture di approfondimento
Apprendimento robotico
U. Nehmzow, T. Mitchell, The prospective student’s introduction to the robot learning problem. Technical Report UMCS-95-12-6, Manchester University, Dept. of Computer Science, Manchester, 1995 (disponibile all’indirizzo: ftp://ftp.cs.man.ac.uk/pub/TR/UMCS-95-12-6.ps.Z).
Apprendimento per rinforzo
A. Barto, Reinforcement learning and reinforcement learning in motor control. In: M. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, pp. 804–813. MIT Press, Cambridge MA, 1995.
D.H. Ballard, An Introduction to Natural Computation, ch. 11. MIT Press, Cambridge MA, 1997.
T. Mitchell, Machine Learning, ch. 13. McGraw-Hill, New York, 1997.
L. Kaelbling, Learning in Embedded Systems. PhD Thesis, Stanford Technical Report, Report No. TR-90-04, 1990. Pubblicato con lo stesso titolo presso MIT Press, Cambridge MA, 1993.
Processi di decisione di Markov
L.P. Kaelbling, M. Littman, A. Cassandra, Planning and acting in partially observable stochastic domains. Artificial Intelligence, vol. 101, 1998.
Percettroni
R. Beale, T. Jackson, Neural Computing: An Introduction, pp. 48–53. Adam Hilger, Bristol, Philadelphia and New York, 1991.
J. Hertz, A. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation, ch. 5. Addison-Wesley, Redwood City CA, 1991.
Percettroni multistrato
D.E. Rumelhart, J.L. McClelland and PDP Research Group, Parallel Distributed Processing, vol. 1 “Foundations”, ch. 8. MIT Press, Cambridge MA, 1986.
J. Hertz, A. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation, pp. 115–120. Addison-Wesley, Redwood City CA, 1991.
Reti con funzione a basi radiali
D. Lowe, Radial basis function networks. In: M. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, pp. 779–782. MIT Press, Cambridge MA, 1995.
C. Bishop, Neural networks for pattern recognition. Oxford University Press, Oxford, 1995.
Mappe auto-organizzanti
T. Kohonen, Self Organization and Associative Memory, ch. 5, 2nd ed. Springer, Berlin-Heidelberg-New York, 1988.
H. Ritter, Self-Organizing Feature Maps: Kohonen Maps. In: M. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, pp. 846–851. MIT Press, Cambridge MA, 1995.
Apprendimento delle macchine
T. Mitchell, Machine learning. McGraw Hill, New York, 1997.
D. Ballard, An introduction to natural computation. MIT Press, Cambridge MA, 1997.
Connessionismo
J. Hertz, A. Krogh, R.G. Palmer, Introduction to the theory of neural computation. Addison-Wesley, Redwood City CA, 1991.
R. Beale, T. Jackson, Neural computing: an introduction. Adam Hilger, Bristol, Philadelphia and New York, 1990.
C. Bishop, Neural networks for pattern recognition. Oxford University Press, Oxford, 1995.
S. Haykin, Neural networks: a comprehensive foundation. Macmillan, New York, 1994.
Caso di studio 3
U. Nehmzow, Vision processing for robot learning. Industrial Robot, vol. 26(2), pp. 121–130, 1999.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Italia
About this chapter
Cite this chapter
Nehmzow, U. (2008). L’apprendimento robotico: dare senso alle informazioni sensoriali. In: Robotica mobile. Unitext(). Springer, Milano. https://doi.org/10.1007/978-88-470-0386-6_4
Download citation
DOI: https://doi.org/10.1007/978-88-470-0386-6_4
Publisher Name: Springer, Milano
Print ISBN: 978-88-470-0385-9
Online ISBN: 978-88-470-0386-6
eBook Packages: Computer ScienceComputer Science (R0)