Sciweavers

585 search results - page 21 / 117
» The Feature Subspace Method for SMT System Combination
Sort
View
SCP
2010
108views more  SCP 2010»
13 years 6 months ago
Combining dynamic and static slicing for analysing assembler
One of the most challenging tasks a programmer can face is attempting to analyse and understand a legacy assembler system. Many features of assembler make analysis difficult, and ...
Martin P. Ward, Hussein Zedan
CORR
2010
Springer
204views Education» more  CORR 2010»
13 years 6 months ago
Predictive State Temporal Difference Learning
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
Byron Boots, Geoffrey J. Gordon
WORDS
2002
IEEE
14 years 24 days ago
Deriving Interaction-Prone Scenarios in Feature Interaction Filtering with Use Case Maps
Feature interactions (FIs, in short) occur when features of different communication services interfere with each other. The FI filtering is a pre-processing before the FI detecti...
Masahide Nakamura, Pattara Leelaprute, Tohru Kikun...
ICIP
2006
IEEE
14 years 9 months ago
Robust Object Detection using Fast Feature Selection from Huge Feature Sets
This paper describes an efficient feature selection method that quickly selects a small subset out of a given huge feature set; for building robust object detection systems. In th...
Duy-Dinh Le, Shin'ichi Satoh
ITS
2004
Springer
124views Multimedia» more  ITS 2004»
14 years 1 months ago
Combining Competing Language Understanding Approaches in an Intelligent Tutoring System
When implementing a tutoring system that attempts a deep understanding of students’ natural language explanations, there are three basic approaches to choose between; symbolic, i...
Pamela W. Jordan, Maxim Makatchev, Kurt VanLehn