We describe the Fourier basis, a linear value function approximation scheme based on the Fourier series. We empirically demonstrate that it performs well compared to radial basis functions and the polynomial basis, the two most popular fixed bases for linear value function approximation, and is competitive with learned proto-value functions.

To effectively organize and analyze massive Web information, in this paper, we have designed a Web classification mining system. BP network has lots of disadvantages, so we have proposed a method that uses RBFNN (Radial Basis Function Neural Network) to classify the text information in Web pages. In this paper, the model of classification system mainly includes RBF (Radial Basis Function) class...

There are multiple reasons why anisotropic basis functions may be needed or be more appropriate. The most obvious is that if the basis function is to be defined on Rn × T then there is no natural norm on this space that would reflect the unique properties of time. A second reason is that function being interpolated or approximated may incorporate a directional dependence. Thirdly, differentiabi...

Dynamic behaviour learning in the face of adversarial opponents involves a) learning a basic set of strategies, and b) tuning these strategies for the specific opponents involved. Iterative approaches to dynamic learning are often slow for large state spaces, especially since in many dynamic situations, the reward is not obvious immediately, but may need to be temporally apportioned over multip...

A hybrid architecture that includes Radial Basis Functions (RBF) and projection based hidden units is introduced together with a simple gradient based training algorithm. Classification and regression results are demonstrated on various data sets and compared with several variants of RBF networks. In particular, best classification results are achieved on the vowel classification data [1].

In this paper we propose a strategy to shape adaptive radial basis functions through potential functions. DYPOF (DYnamic POtential Functions) neural network (NN) is designed based on radial basis functions (RBF) NN with a two-stage training procedure. Static (fixed number of RBF) and dynamic (ability to add or delete one or more RBF) versions of our learning algorithm are introduced. We investi...

Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and practical applications. This paper proposes a Hierarchical Radial Basis Function Network (HiRBF) model for forecasting three major international currency exchange rates. Based on the pre-defined instruction sets, HRBF model can be created and evolved. The ...

This paper proposes a neural-network-based method for the computation of the configuration space for robotic manipulators. The configuration space can be obtained by repeatedly computing configuration space patterns for elementary obstacle primitives. For any manipulator, these patterns depend only on the distance between the base of the manipulator and the obstacle primitive. An RBF-network is...

The problem is said to be tractable if there exist constants c, α, β independent of q (but possibly dependent on μ and F) such that En(F , μ) ≤ cqαn−β. We explore different regions (including manifolds), function classes, and measures for which this problem is tractable. Our results include tractability theorems for integration with respect to non-tensor product measures, and over unbounded and...

In this paper, we deal with the problem of function approximation from a given set of input/output data. This problem consists of analyzing these training examples so that we can predict the output of the model given new inputs. We present a new method for function approximation of the I/O data using radial basis functions (RBFs). This approach is based on a new efficient method of clustering o...