Ron Sun. Introduction to sequence learning. In Ron Sun and Lee Giles, editors, Sequence Learning: Paradigms, Algorithms, and Applications, pages 1--10. Springer-Verlag, 2000. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Predictive Autonomous Robot Navigation - Foka (2002) (1 citation) (Correct)
....of the belief state. Recently, it has been proposed to concatenate the MLS with the entropy [40] to form a set of jointly statistics that represents the belief state and thus be able to recover the true model. Reinforcement learning methods such as Q learning have also been used to solve POMDPs [37, 50, 49, 48, 51, 22, 13]. Finally, evolutionary algorithms for reinforcement learning can be used in conjunction with the traditional reinforcement learning techniques [27] 2.1.2 Learning POMDP s Learning POMDPs involves determining the structure of the POMDP, initialize the probability matrices of that structure and ....
Ron Sun. Introduction to sequence learning. In Ron Sun and Lee Giles, editors, Sequence Learning: Paradigms, Algorithms, and Applications, pages 1--10. Springer-Verlag, 2000.
Neural Networks With Small Weights Implement Finite Memory.. - Hammer, Tino (2002) (Correct)
....UCED property and hence are distribution independent PAC learnable unlike general recurrent networks. 1 Introduction Data of interest have a sequential structure in a wide variety of application areas such as language processing, time series prediction, financial forecasting, or DNA sequences [25, 35]. Recurrent neural networks and hidden Markov models constitute very powerful methods which have been successfully applied to these problems, see for example [2, 11, 24, 26] Successful applications are accompanied by theoretical investigations which demonstrate the capacities of recurrent ....
R. Sun, Introduction to sequence learning. R. Sun, C.L. Giles (eds.), Sequence Learning: Paradigms, Algorithms, and Applications, pp. 1-10, Springer, 2001.
Neural Networks With Small Weights Implement Finite Memory.. - Hammer, Tino (2002) (Correct)
....UCED property and hence are distribution independent PAC learnable unlike general recurrent networks. 1 Introduction Data of interest have a sequential structure in a wide variety of application areas such as language processing, time series prediction, financial forecasting, or DNA sequences [25, 34]. Recurrent neural networks and hidden Markov models constitute very powerful methods which have been successfully applied to these problems, see for example [2, 11, 24, 26] Successful applications are accompanied by theoretical investigations which demonstrate the capacities of recurrent ....
R. Sun, Introduction to sequence learning. R. Sun, C.L. Giles (eds.), Sequence Learning: Paradigms, Algorithms, and Applications, pp. 1-10, Springer, 2001.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC