Paper Info
Title
Convolutional Neural Support Vector Machines: Hybrid Visual Pattern Classifiers for Multi-robot Systems
Abstract
We introduce Convolutional Neural Support Vector Machines (CNSVMs), a combination of two heterogeneous supervised classification techniques, Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). CNSVMs are trained using a Stochastic Gradient Descent approach, that provides the computational capability of online incremental learning and is robust for typical learning scenarios in which training samples arrive in mini-batches. This is the case for visual learning and recognition in multi-robot systems, where each robot acquires a different image of the same sample. The experimental results indicate that the CNSVM can be successfully applied to visual learning and recognition of hand gestures as well as to measure learning progress.
Year
DOI
Venue
2012
10.1109/ICMLA.2012.14
ICMLA (1)
Keywords
Field
DocType
support vector machines,hybrid visual pattern classifiers,typical learning scenario,online incremental learning,stochastic gradient descent approach,convolutional neural support,computational capability,convolutional neural networks,visual learning,vector machines,multi-robot systems,different image,mobile robots,learning artificial intelligence,image classification,neural nets
Competitive learning,Online machine learning,Semi-supervised learning,Pattern recognition,Active learning (machine learning),Computer science,Convolutional neural network,Learning vector quantization,Artificial intelligence,Deep learning,Artificial neural network,Machine learning
Conference
Volume
ISBN
Citations 
1
978-1-4673-4651-1
5
PageRank 
References 
Authors
0.48
0
6
Name
Order
Citations
PageRank
Jawad Nagi114811.42
Gianni A. Di Caro272151.79
Alessandro Giusti3102392.34
Farrukh Nagi4877.29
Luca Maria Gambardella57926726.40
Di Caro, G.A.6646.24