Sciweavers

4930 search results - page 371 / 986
» Learning minimal abstractions
Sort
View
ICONIP
2008
15 years 8 months ago
On Node-Fault-Injection Training of an RBF Network
Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
John Sum, Chi-Sing Leung, Kevin Ho
ML
2006
ACM
148views Machine Learning» more  ML 2006»
15 years 6 months ago
Melodic analysis with segment classes
This paper presents a representation for melodic segment classes and applies it to music data mining. Melody is modeled as a sequence of segments, each segment being a sequenceofno...
Darrell Conklin
ECAI
2000
Springer
15 years 11 months ago
Autonomous Environment and Task Adaptation for Robotic Agents
This paper investigates the problem of improving the performance of general state-of-the-art robot control systems by autonomously adapting them to specific tasks and environments...
Michael Beetz, Thorsten Belker
AAAI
2007
15 years 9 months ago
Recognizing Textual Entailment Using a Subsequence Kernel Method
We present a novel approach to recognizing Textual nt. Structural features are constructed from abstract tree descriptions, which are automatically extracted from syntactic depend...
Rui Wang 0005, Günter Neumann
ML
2006
ACM
15 years 6 months ago
Type-sensitive control-flow analysis
Higher-order typed languages, such as ML, provide strong support for data and type abn. While such abstraction is often viewed as costing performance, there are situations where i...
John H. Reppy