Sciweavers

1131 search results - page 86 / 227
» Generalization Improvement in Multi-Objective Learning
Sort
View
ICIAP
2009
ACM
16 years 29 days ago
Towards a Theoretical Framework for Learning Multi-modal Patterns for Embodied Agents
Multi-modality is a fundamental feature that characterizes biological systems and lets them achieve high robustness in understanding skills while coping with uncertainty. Relativel...
Nicoletta Noceti, Barbara Caputo, Claudio Castelli...
ICRA
2009
IEEE
259views Robotics» more  ICRA 2009»
16 years 25 days ago
Constructing action set from basis functions for reinforcement learning of robot control
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawar...
ICRA
2008
IEEE
229views Robotics» more  ICRA 2008»
16 years 19 days ago
Learning of moving cast shadows for dynamic environments
Abstract— We propose a novel online framework for detecting moving shadows in video sequences using statistical learning techniques. In this framework, Support Vector Machines ar...
Ajay J. Joshi, Nikolaos Papanikolopoulos
ISCAS
2008
IEEE
145views Hardware» more  ISCAS 2008»
16 years 18 days ago
Group learning using contrast NMF : Application to functional and structural MRI of schizophrenia
— Non-negative Matrix factorization (NMF) has increasingly been used as a tool in signal processing in the last couple of years. NMF, like independent component analysis (ICA) is...
Vamsi K. Potluru, Vince D. Calhoun
ECML
2007
Springer
16 years 11 days ago
Roulette Sampling for Cost-Sensitive Learning
In this paper, we propose a new and general preprocessor algorithm, called CSRoulette, which converts any cost-insensitive classification algorithms into cost-sensitive ones. CSRou...
Victor S. Sheng, Charles X. Ling