Sciweavers

166 search results - page 18 / 34
» Automatically searching near-optimal artificial neural netwo...
Sort
View
AIIA
2001
Springer
14 years 1 months ago
Wide Coverage Incremental Parsing by Learning Attachment Preferences
This paper presents a novel method for wide coverage parsing using an incremental strategy, which is psycholinguistically motivated. A recursive neural network is trained on treeba...
Fabrizio Costa, Vincenzo Lombardo, Paolo Frasconi,...
VISUAL
2005
Springer
14 years 2 months ago
Automatic Redeye Removal for Smart Enhancement of Photos of Unknown Origin
The paper describes a modular procedure for automatic correction of redeye artifact in images of unknown origin, maintaining the natural appearance of the eye. First, a smart color...
Francesca Gasparini, Raimondo Schettini
PAA
2006
13 years 8 months ago
Automatic name extraction from degraded document images
The problem addressed in this paper is the automatic extraction of names from a document image. Our approach relies on the combination of two complementary analyses. First, the ima...
Laurence Likforman-Sulem, Pascal Vaillant, Aliette...
FSKD
2005
Springer
180views Fuzzy Logic» more  FSKD 2005»
14 years 2 months ago
An Effective Feature Selection Scheme via Genetic Algorithm Using Mutual Information
Abstract. In the artificial neural networks (ANNs), feature selection is a wellresearched problem, which can improve the network performance and speed up the training of the networ...
Chunkai K. Zhang, Hong Hu
AI
2002
Springer
13 years 8 months ago
Programming backgammon using self-teaching neural nets
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Gerald Tesauro