José Ricardo Gonçalves Manzan

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
ICAI This work proposes a mathematical proof for the use of orthogonal bipolar vectors (OBV) rather than conventional target vectors in artificial neural network MLP learning. A larger Euclidean distance provided by new target vectors is explored to improve the learning and generalization abilities of MLPs. The proposed proof compares the MLP performances(More)
This paper proposes the use of new target vectors for MLP learning in EEG signal classification. A large Euclidean distance provided by orthogonal bipolar vectors as new target ones is explored to improve the learning and generalization abilities of MLPs. The data set consisted of EEG signals captured from normal individuals and individuals under(More)
  • 1