TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Kopinski, Thomas
A1  - Gepperth, Alexander
A1  - Handmann, Uwe
T1  - A simple technique for improving multi- class classification with neural networks
T2  - In 23th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2015),  Bruges, Belgium
N2  - We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task.
Y1  - 2015
U6  - https://doi.org/https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-136.pdf
DO  - https://doi.org/https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-136.pdf
SP  - 469
EP  - 474
S1  - 5
ER  -