Sciweavers

595 search results - page 65 / 119
» Terrain mapping and classification using neural networks
Sort
View
ESANN
2000
14 years 11 months ago
Local input-output stability of recurrent networks with time-varying weights
Abstract. We present local conditions for input-output stability of recurrent neural networks with time-varying parameters introduced for instance by noise or on-line adaptation. T...
Jochen J. Steil
IJISTA
2007
124views more  IJISTA 2007»
14 years 9 months ago
Incremental learning for spoken affect classification and its application in call-centres
: This paper introduces a system for real-time incremental learning in a call-centre environment. The classifier used is a Support Vector Machine (SVM) and it is applied to telepho...
Donn Morrison, Ruili Wang, W. L. Xu, Liyanage C. D...
CLEF
2010
Springer
14 years 11 months ago
myClass: A Mature Tool for Patent Classification
In this task 2,000 patents in three languages (English, French and German) were to be classified among approximately 600 categories. We used a classifier based on neural networks ...
Jacques Guyot, Karim Benzineb, Gilles Falquet
ML
2006
ACM
110views Machine Learning» more  ML 2006»
14 years 9 months ago
Classification-based objective functions
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
Michael Rimer, Tony Martinez
ROBIO
2006
IEEE
153views Robotics» more  ROBIO 2006»
15 years 3 months ago
GA-based Feature Subset Selection for Myoelectric Classification
– This paper presents an ongoing investigation to select optimal subset of features from set of well-known myoelectric signals (MES) features in time and frequency domains. Four ...
Mohammadreza Asghari Oskoei, Huosheng Hu