Sample Sizes for Multiple Output Threshold Networks.
This paper applies the theory of probably approximately correct (PAC) learning to multiple-output feedforward threshold networks. It is shown that the sample size for reliable learning can be bounded above by a quantity independent of the number of outputs of the network
|Title:||Sample Sizes for Multiple Output Threshold Networks|
|UCL classification:||UCL > School of BEAMS
UCL > School of BEAMS > Faculty of Engineering Science
Archive Staff Only