could you tell(remind) us how to get started using gnubg-nn for training of the neural nets. What I would like to know is
A) how is it decided which net (normal/race/crashed) that is used. B) are the crashed and normal nets different in their design or are they just trained against different sets of positions
C) how to train a net by self-play (TD training?) D) how to train a net against a database of positions