Sciweavers

394 search results - page 35 / 79
» Comparative Exudate Classification Using Support Vector Mach...
Sort
View
ICML
2007
IEEE
14 years 9 months ago
An empirical evaluation of deep architectures on problems with many factors of variation
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
IJCNN
2007
IEEE
14 years 2 months ago
Local Learning of Tide Level Time Series using a Fuzzy Approach
— Forecasting the tide level in the Venezia lagoon is a very compelling task. In this work we propose a new approach to the learning of tide level time series based on the local ...
E. Canestrelli, P. Canestrelli, Marco Corazza, Mau...
ICANN
2007
Springer
14 years 2 months ago
Selection of Basis Functions Guided by the L2 Soft Margin
Support Vector Machines (SVMs) for classification tasks produce sparse models by maximizing the margin. Two limitations of this technique are considered in this work: firstly, th...
Ignacio Barrio, Enrique Romero, Lluís Belan...
PR
2007
165views more  PR 2007»
13 years 8 months ago
A trainable feature extractor for handwritten digit recognition
This article focusses on the problems of feature extraction and the recognition of handwritten digits. A trainable feature extractor based on the LeNet5 convolutional neural netwo...
Fabien Lauer, Ching Y. Suen, Gérard Bloch
IROS
2006
IEEE
126views Robotics» more  IROS 2006»
14 years 2 months ago
A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks
Abstract— Tying suture knots is a time-consuming task performed frequently during Minimally Invasive Surgery (MIS). Automating this task could greatly reduce total surgery time f...
Hermann Georg Mayer, Faustino J. Gomez, Daan Wiers...