Convolutional Neural Support Vector Machines: Hybrid Visual Pattern Classifiers for Multi-robot Systems

Jawad Nagi, Gianni A. Di Caro, Alessandro Giusti, Farrukh Nagi, Luca M. Gambardella
2012 2012 11th International Conference on Machine Learning and Applications  
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
more » ... 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.
doi:10.1109/icmla.2012.14 dblp:conf/icmla/NagiCGNG12 fatcat:sec25kn2sjh6pnopja5e663uxy