Number Theoretic Transforms in Neural Network Image Classiication

@inproceedings{Harte1997NumberTT,
  title={Number Theoretic Transforms in Neural Network Image Classiication},
  author={Thomas Harte and Rudolf Hanka},
  year={1997}
}
Judicious use of number theory and abstract algebra can increase the eeciency of neural network pattern classiiers. We use the example of our neural network tissue classiication of MRI of the breast to illustrate that eecient pattern recognition algorithms can be designed from algebraic fundamentals. The algorithm is based on number theoretic transform… CONTINUE READING