Package rdkit :: Package ML :: Package Neural :: Module Trainers
[hide private]
[frames] | no frames]

Module Trainers

source code

Training algorithms for feed-forward neural nets

Unless noted otherwise, algorithms and notation are taken from:
"Artificial Neural Networks: Theory and Applications",
  Dan W. Patterson, Prentice Hall, 1996

Classes [hide private]
  Trainer
"virtual base class" for network trainers
  BackProp
implement back propagation (algorithm on pp 153-154 of Patterson)
Variables [hide private]
  __package__ = 'rdkit.ML.Neural'

Imports: numpy