The Convergence Rate for a K-Functional in Learning Theory
نویسندگان
چکیده
It is known that in the field of learning theory based on reproducing kernel Hilbert spaces the upper bounds estimate for a K-functional is needed. In the present paper, the upper bounds for the K-functional on the unit sphere are estimated with spherical harmonics approximation. The results show that convergence rate of the K-functional depends upon the smoothness of both the approximated function and the reproducing kernels.
منابع مشابه
Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon...
متن کاملCystoscopy Image Classication Using Deep Convolutional Neural Networks
In the past three decades, the use of smart methods in medical diagnostic systems has attractedthe attention of many researchers. However, no smart activity has been provided in the eld ofmedical image processing for diagnosis of bladder cancer through cystoscopy images despite the highprevalence in the world. In this paper, two well-known convolutional neural networks (CNNs) ...
متن کاملHydrogen Abstraction Reaction of Hydroxyl Radical with 1,1-Dibromoethane and 1,2-Dibromoethane Studied by Using Semi-Classical Transition State Theory
The hydrogen abstraction reaction by OH radical from CH2BrCH2Br (R1) and CH₃CHBr2 (R2) is investigated theoretically by semi-classical transition state theory. The stationary points for both reactions are located by using ωB97X-D and KMLYP density functional methods along with cc-pVTZ basis. Single-point energy calculations are performed at the QCISD(T) and CCSD(T) levels of theory with differe...
متن کاملA Higher Order Online Lyapunov-Based Emotional Learning for Rough-Neural Identifiers
o enhance the performances of rough-neural networks (R-NNs) in the system identification, on the base of emotional learning, a new stable learning algorithm is developed for them. This algorithm facilitates the error convergence by increasing the memory depth of R-NNs. To this end, an emotional signal as a linear combination of identification error and its differences is used to achie...
متن کاملNatural Bond Orbital (NBO) Study of (5H-tetrazol-1-yl)(triphenylphosphine)gold [Au(tetz)(PPh3)]
In this research work, we studied theoretically the structural properties of (5H-tetrazol-1-yl)(triphenylphosphine)gold or [Au(tetz)(PPh3)] by density functional theory (DFT) method at LANL2DZ level. All calculations were performed at 298.15 K and 1 atmosphere. Firstly, the bond lengths, bond angles, dihedral angles and natural charge density on atoms of the compound were calculated. The depend...
متن کامل