Paper Info
Title
Incremental learning for visual classification using Neural Gas
Abstract
In this paper we investigate a novel algorithm for solving classification problems in an action-oriented perception framework supported by visual feedback. The approach is based on an extension of the Neural Gas with local Principal Component Analysis (NGPCA) algorithm. As an abstract Recurrent Neural Network (RNN) this model is able to complete a partially given pattern. Under this point of view it is possible to generalize the model as a supervised classifier in which for a given segmented object (i.e. with particular visual cues) the class variable is retrieved as the network outputs. An incremental version of the algorithm is also presented and applied in a robotic platform for object manipulation tasks.
Year
DOI
Venue
2010
10.1109/IJCNN.2010.5596594
Neural Networks
Keywords
Field
DocType
learning (artificial intelligence),principal component analysis,recurrent neural nets,NGPCA algorithm,action-oriented perception framework,incremental learning,neural gas,neural gas with local principal component analysis,object manipulation tasks,recurrent neural network,robotic platform,visual classification,visual feedback
Sensory cue,Algorithm design,Pattern recognition,Computer science,Visualization,Recurrent neural network,Image segmentation,Artificial intelligence,Classifier (linguistics),Class variable,Neural gas,Machine learning
Conference
ISSN
ISBN
Citations 
1098-7576
978-1-4244-6916-1
0
PageRank 
References 
Authors
0.34
6
3
Name
Order
Citations
PageRank
Ignazio Aleo100.34
Paolo Arena226147.43
Luca Patané310417.31