Sciweavers

715 search results - page 75 / 143
» Neural Network with Matrix Inputs
Sort
View
NN
2006
Springer
153views Neural Networks» more  NN 2006»
13 years 8 months ago
An incremental network for on-line unsupervised classification and topology learning
This paper presents an on-line unsupervised learning mechanism for unlabeled data that are polluted by noise. Using a similarity thresholdbased and a local error-based insertion c...
Shen Furao, Osamu Hasegawa
ICDAR
2003
IEEE
14 years 2 months ago
A Neural-Evolutionary Approach for Feature and Architecture Selection in Online Handwriting Recognition
An automatic recognition of online handwritten text has been an on-going research problem for nearly four decades. It has been gaining more interest due to the increasing populari...
Brijesh Verma, Moumita Ghosh
WSCG
2004
188views more  WSCG 2004»
13 years 10 months ago
Recognition of Motor Imagery Electroencephalography Using Independent Component Analysis and Machine Classifiers
Motor imagery electroencephalography (EEG), which embodies cortical potentials during mental simulation of left or right finger lifting tasks, can be used as neural input signals ...
Chih-I. Hung, Po-Lei Lee, Yu-Te Wu, Hui-Yun Chen, ...
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
14 years 24 days ago
Bounds for the computational power and learning complexity of analog neural nets
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
Wolfgang Maass
ICANN
2005
Springer
14 years 2 months ago
Mutual Information and k-Nearest Neighbors Approximator for Time Series Prediction
This paper presents a method that combines Mutual Information and k-Nearest Neighbors approximator for time series prediction. Mutual Information is used for input selection. K-Nea...
Antti Sorjamaa, Jin Hao, Amaury Lendasse