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...
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...
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...
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...
— 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...