Sciweavers

1413 search results - page 153 / 283
» ideas 2007
Sort
View
IJCAI
1997
15 years 7 months ago
Extracting Propositions from Trained Neural Networks
This paper presents an algorithm for extract­ ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
Hiroshi Tsukimoto
SBBD
2000
168views Database» more  SBBD 2000»
15 years 7 months ago
Fast Feature Selection Using Fractal Dimension
Dimensionalitycurse and dimensionalityreduction are two issues that have retained highinterest for data mining, machine learning, multimedia indexing, and clustering. We present a...
Caetano Traina Jr., Agma J. M. Traina, Leejay Wu, ...
IJCAI
1993
15 years 7 months ago
Learning Finite Automata Using Local Distinguishing Experiments
One of the open problems listed in Rivest and Schapire, 1989] is whether and how that the copies of L in their algorithm can be combined into one for better performance. This pape...
Wei-Mein Shen
MVA
1996
142views Computer Vision» more  MVA 1996»
15 years 7 months ago
Interactive Image Segmentation System for Visual Simulation
To use photographs in visual simulation such as synthesizing new images by overlapping an object in an image onto the other, physically significant regions corresponding to object...
Makoto Kato
ACL
1992
15 years 7 months ago
Information States as First Class Citizens
The information state of an agent is changed when a text (in natural language) is processed. The meaning of a text can be taken to be this information state change potential. The ...
Jørgen Villadsen