Sciweavers

3718 search results - page 89 / 744
» On learning with dissimilarity functions
Sort
View
CORR
2012
Springer
214views Education» more  CORR 2012»
12 years 5 months ago
Sum-Product Networks: A New Deep Architecture
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most general conditions under...
Hoifung Poon, Pedro Domingos
ECTEL
2010
Springer
13 years 7 months ago
Demands of Modern PLEs and the ROLE Approach
Abstract. We present basic concepts and an outlook on current approaches and techniques of personal learning environments to point out their demands, focussing on recommendations i...
Uwe Kirschenmann, Maren Scheffel, Martin Friedrich...
ICML
1995
IEEE
14 years 10 months ago
Stable Function Approximation in Dynamic Programming
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
Geoffrey J. Gordon
ICRA
1994
IEEE
105views Robotics» more  ICRA 1994»
14 years 1 months ago
Harmonic Functions and Collision Probabilities
There is a close relationship between harmonic functions { which have recently been proposed for path planning { and hitting probabilities for random processes. The hitting probab...
Christopher I. Connolly
NPL
2006
109views more  NPL 2006»
13 years 9 months ago
CB3: An Adaptive Error Function for Backpropagation Training
Effective backpropagation training of multi-layer perceptrons depends on the incorporation of an appropriate error or objective function. Classification-based (CB) error functions ...
Michael Rimer, Tony Martinez