Sciweavers

1359 search results - page 75 / 272
» Neural Dynamics with Stochasticity
Sort
View
JMLR
2008
129views more  JMLR 2008»
15 years 6 months ago
Finite-Time Bounds for Fitted Value Iteration
In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...
Rémi Munos, Csaba Szepesvári
AIA
2006
15 years 7 months ago
A Recurrent Neural Filter for Adaptive Noise Cancellation
This paper presents a dynamic neural filter for adaptive noise cancellation. The cancellation task is transformed to a system-identification problem, which is tackled by use of th...
Paris A. Mastorocostas, Dimitris N. Varsamis, Cons...
TNN
2010
139views Management» more  TNN 2010»
15 years 25 days ago
Identification of finite state automata with a class of recurrent neural networks
A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in...
Sung Hwan Won, Iickho Song, Sun-Young Lee, Cheol H...
ICANN
2009
Springer
16 years 21 days ago
Simbed: Similarity-Based Embedding
Simbed, standing for similarity-based embedding, is a new method of embedding high-dimensional data. It relies on the preservation of pairwise similarities rather than distances. I...
John Aldo Lee, Michel Verleysen
CDC
2008
IEEE
110views Control Systems» more  CDC 2008»
16 years 18 days ago
Multistage investments with recourse: A single-asset case with transaction costs
— We consider a financial decision problem involving dynamic investment decisions on a single risky instrument over multiple and discrete time periods. Investment returns are as...
Ufuk Topcu, Giuseppe Carlo Calafiore, Laurent El G...