Re: [R] Improve training of predictive neural networks

Inline. -- Bert Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it." -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) On Wed, Jan 13, 2016 at 2:55 PM, Luigi Marongiu wrote: > Dear all, > I

[R] Improve training of predictive neural networks

Dear all, I am trying to train a predictive neural network to guess the positivity/negativity of some tests I have done. I am using the library pnn and I have empirically identified the best sigma to use in the algorithm but the results I got are affected by false positive results. The actual