Sciweavers

536 search results - page 72 / 108
» Residual Algorithms: Reinforcement Learning with Function Ap...
Sort
View
IEEECIT
2009
IEEE
14 years 2 months ago
Clustering of Software Systems Using New Hybrid Algorithms
—Software clustering is a method for increasing software system understanding and maintenance. Software designers, first use MDG graph to model the structure of software system. ...
Ali Safari Mamaghani, Mohammad Reza Meybodi
ATAL
2009
Springer
14 years 2 months ago
Transfer via soft homomorphisms
The field of transfer learning aims to speed up learning across multiple related tasks by transferring knowledge between source and target tasks. Past work has shown that when th...
Jonathan Sorg, Satinder Singh
SDM
2008
SIAM
150views Data Mining» more  SDM 2008»
13 years 9 months ago
A Stagewise Least Square Loss Function for Classification
This paper presents a stagewise least square (SLS) loss function for classification. It uses a least square form within each stage to approximate a bounded monotonic nonconvex los...
Shuang-Hong Yang, Bao-Gang Hu
ICRA
2006
IEEE
165views Robotics» more  ICRA 2006»
14 years 1 months ago
Biped Gait Optimization using Spline Function based Probability Model
— A new Estimation of Distribution Algorithm (EDA) with spline kernel function (EDA_S) is proposed to optimize biped gait for a nine-link humanoid robot. Gait synthesis of the bi...
Lingyun Hu, Changjiu Zhou, Zengqi Sun
TNN
2008
82views more  TNN 2008»
13 years 7 months ago
Deterministic Learning for Maximum-Likelihood Estimation Through Neural Networks
In this paper, a general method for the numerical solution of maximum-likelihood estimation (MLE) problems is presented; it adopts the deterministic learning (DL) approach to find ...
Cristiano Cervellera, Danilo Macciò, Marco ...