Sciweavers

19 search results - page 4 / 4
» A multi-objective approach to RBF network learning
Sort
View
KES
2005
Springer
13 years 10 months ago
Relative Magnitude of Gaussian Curvature from Shading Images Using Neural Network
Abstract. A new approach is proposed to recover the relative magnitude of Gaussian curvature from three shading images using neural network. Under the assumption that the test obje...
Yuji Iwahori, Shinji Fukui, Chie Fujitani, Yoshino...
ACCV
2006
Springer
13 years 7 months ago
Learning Multi-category Classification in Bayesian Framework
Abstract. We propose an algorithm for Sparse Bayesian Classification for multi-class problems using Automatic Relevance Determination(ARD). Unlike other approaches which treat mult...
Atul Kanaujia, Dimitris N. Metaxas
ICIG
2009
IEEE
13 years 3 months ago
Statistical Modeling of Optical Flow
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...
Dongmin Ma, Véronique Prinet, Cyril Cassisa
IJCNN
2007
IEEE
13 years 11 months ago
Agnostic Learning versus Prior Knowledge in the Design of Kernel Machines
Abstract— The optimal model parameters of a kernel machine are typically given by the solution of a convex optimisation problem with a single global optimum. Obtaining the best p...
Gavin C. Cawley, Nicola L. C. Talbot