Sciweavers

361 search results - page 3 / 73
» Minimization of Error Functionals over Perceptron Networks
Sort
View
ML
2006
ACM
110views Machine Learning» more  ML 2006»
13 years 5 months ago
Classification-based objective functions
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
Michael Rimer, Tony Martinez
ICARCV
2006
IEEE
126views Robotics» more  ICARCV 2006»
13 years 11 months ago
Improvement to the Minimization of Hybrid Error Functions for Pose Alignment
— Many problems in computer vision such as pose recovery and structure estimation are formulated as a minimization process. These problems vary in the use of image measurements d...
A. H. Abdul Hafez, C. V. Jawahar
IJCNN
2006
IEEE
13 years 11 months ago
Improving the Convergence of Backpropagation by Opposite Transfer Functions
—The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately ...
Mario Ventresca, Hamid R. Tizhoosh
IJCNN
2007
IEEE
14 years 2 days ago
A Functional Link Network With Ordered Basis Functions
—A procedure is presented for selecting and ordering the polynomial basis functions in the functional link net (FLN). This procedure, based upon a modified Gram Schmidt orthonorm...
Saurabh Sureka, Michael T. Manry
JMLR
2006
106views more  JMLR 2006»
13 years 5 months ago
Stability Properties of Empirical Risk Minimization over Donsker Classes
We study some stability properties of algorithms which minimize (or almost-minimize) empirical error over Donsker classes of functions. We show that, as the number n of samples gr...
Andrea Caponnetto, Alexander Rakhlin