Novelty Detection and Neural Network

@inproceedings{ValidationChris1994NoveltyDA,
  title={Novelty Detection and Neural Network},
  author={ValidationChris and M.. and BishopNeural and ScienceAston and UniversityBirmingham},
  year={1994}
}
  • ValidationChris, M.., +2 authors UniversityBirmingham
  • Published 1994
One of the key factors limiting the use of neural networks in many industrial applications has been the diiculty of demonstrating that a trained network will continue to generate reliable outputs once it is in routine use. An important potential source of errors arises from novel input data, that is input data which diier signiicantly from the data used to… CONTINUE READING