Training to a Neural Net's Inherent Bias

@inproceedings{Gutstein2009TrainingTA,
  title={Training to a Neural Net's Inherent Bias},
  author={Steven Gutstein and Olac Fuentes and Eric Freudenthal},
  booktitle={FLAIRS Conference},
  year={2009}
}
A neural net with multiple output nodes is capable of distinguishing among a set of related input classes even in the absence of training. It can do so with an accuracy that is markedly better than random guessing. This is because each class will tend to activate a different set of output nodes. We refer to this tendency as the net’s ’inherent’ bias… CONTINUE READING