Complexity bounds of radial basis functions and multi-objective learning
نویسندگان
چکیده
In the paper, the problem of multi-objective (MOBJ) learning is discussed. The problem of obtaining apparent (effective) complexity measure, which is one of the objectives, is considered. For the specific case of RBFN, the bounds on the smoothness-based complexity measure are proposed. As shown in the experimental part, the bounds can be used for Pareto set approximation.
منابع مشابه
Radial Basis Function Networks and Complexity Regularization in Function Learning
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function network. Our approach differs from previous complexity regularization neural-network function learning schemes in that we operate with random covering numbers and l(1) metric entropy, making it possible to consider much br...
متن کاملProviding a Method for Solving Interval Linear Multi-Objective Problems Based on the Goal Programming Approach
Most research has focused on multi-objective issues in its definitive form, with decision-making coefficients and variables assumed to be objective and constraint functions. In fact, due to inaccurate and ambiguous information, it is difficult to accurately identify the values of the coefficients and variables. Interval arithmetic is appropriate for describing and solving uncertainty and inaccu...
متن کاملDesign of Grounding Vertical Rods Buried in Complex Soils using Radial Basis Functions
In this paper, using neural networks based on radial basis functions (RBF), a comprehensive closed-form solution for effective length of vertical grounding rod is extracted in such a way that the two effects of ionization and dispersion are simultaneously considered. In creating the model, training data are computed from multi-conductor transmission line (MTL). As a results, firstly in the prop...
متن کاملBasis Function Networks and Complexity
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function network. Our approach differs from the previous complexity regularization neural network function learning schemes in that we operate with random covering numbers and 11 metric entropy, making it po~sibleto consider much b...
متن کاملRadial basis function network based on time variant multi-objective particle swarm optimization for medical diseases diagnosis
This paper proposes an adaptive evolutionary radial basis function (RBF) network algorithm to evolve accuracy and connections (centers and weights) of RBF networks simultaneously. The problem of hybrid learning of RBF network is discussed with the multi-objective optimization methods to improve classification accuracy for medical disease diagnosis. In this paper, we introduce a time variant mul...
متن کامل