Abstract
This paper presents a new probabilistic neural network model, called IPNN (for Incremental Probabilistic Neural Network), which is able to learn continuously probability distributions from data flows. The proposed model is inspired by the Specht’s general regression neural network, but have several improvements which makes it more suitable to be used on-line in and robotic tasks. Moreover, IPNN is able to automatically define the network structure in an incremental way, with new units added whenever necessary to represent new training data. The performed experiments shows that IPNN is very useful in regression and reinforcement learning tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Specht, D.: Probabilistic neural networks for classification, mapping, or associative memory. In: Proc. IEEE Int. Conf. Neural Networks, San Diego, CA, vol. 1, pp. 525–532 (July 1988)
Specht, D.F.: Probabilistic neural networks. Neural Networks 3, 109–118 (1990)
Rutkowski, L.: Adaptive probabilistic neural networks for pattern classification in time-varying environment. IEEE Trans. Neural Networks 15(4), 811–827 (2004)
Tråvén, H.G.H.: A neural network approach to statistical pattern classification by “semiparametric” estimation of probability density functions. IEEE Trans. Neural Networks 2(3), 366–377 (1991)
Specht, D.F.: A general regression neural network. IEEE Trans. Neural Networks 2(6), 568–576 (1991)
Montana, D.: A weighted probabilistic neural network. In: Advances in Neural Information Processing Systems, vol. 4, pp. 1110–1117. Morgan Kaufmann, San Francisco (1992)
Ćwik, J., Koronacki, J.: Probability density estimation using a gaussian clustering algorithm. Neural Computing and Applications 4, 149–160 (1996)
Berthold, M.R., Diamond, J.: Constructive training of probabilistic neural networks. Neurocomputing 19, 167–183 (1998)
Delgosha, F., Menhaj, M.B.: Fuzzy probabilistic neural networks: A practical approach to the implementation of bayesian classifier. In: Reusch, B. (ed.) Fuzzy Days 2001. LNCS, vol. 2206, pp. 76–85. Springer, Heidelberg (2001)
Chang, R.K.Y., Loo, C.K., Rao, M.V.C.: Enhanced probabilistic neural network with data imputation capabilities for machine-fault classification. Neural Computing and Applications 18, 791–800 (2009)
Polat, O., Yildirim, T.: FPGA implementation of a general regression neural network: An embedded pattern classification system. Digital Signal Processing 20, 881–886 (2010)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society 39(1), 1–38 (1977)
Tan, P.N., Steinbach, M., Kumar, V.: Introduction to Data Mining. Addison-Wesley, Boston (2006)
Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. In: Intelligent Robotics and Autonomous Agents. MIT Press, Cambridge (2006)
Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice-Hall, Upper Saddle River (2008)
Engel, P.M., Heinen, M.R.: Incremental learning of multivariate gaussian mixture models. In: Proc. 20th Brazilian Symposium on AI (SBIA), São Bernardo do Campo, SP, Brazil. LNCS. Springer, Heidelberg (October 2010) (to appear)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Utsunomiya, H., Shibata, K.: Learning with a recurrent neural network in a continuous state and action space task. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008, Part II. LNCS, vol. 5507, pp. 970–978. Springer, Heidelberg (2009)
Doya, K.: Reinforcement learning in continuous time and space. Neural Computation 12(1), 219–245 (2000)
Basso, E.W., Engel, P.M.: Reinforcement learning in non-stationary continuous time and space scenarios. In: Anais do VII Brazilian Meeting on Artificial Intelligence ENIA, Bento Gonçalves, RS, Brazil. SBC Press (2009)
Smart, W.D.: Making Reinforcement Learning Work on Real Robots. Ph.d. thesis, Brown Univ., Providence, Rhode Island (May 2002)
Doya, K.: Temporal difference learning in continuous time and space. In: Advances in Neural Information Processing Systems, vol. 8, pp. 1073–1079 (1996)
Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks 1, 4–27 (1990)
Nolfi, S., Tani, J.: Extracting regularities in space and time through a cascade of prediction networks: The case of a mobile robot navigating in a structured environment. Connection Science 11(2), 125–148 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Heinen, M.R., Engel, P.M. (2010). An Incremental Probabilistic Neural Network for Regression and Reinforcement Learning Tasks. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6353. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15822-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-15822-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15821-6
Online ISBN: 978-3-642-15822-3
eBook Packages: Computer ScienceComputer Science (R0)