Skip to content

Latest commit

 

History

History
11 lines (9 loc) · 336 Bytes

README.md

File metadata and controls

11 lines (9 loc) · 336 Bytes

neural-net-hacking-examples

Roadmap

  • Add bias neuron
  • Calculate error
  • Backprop error
  • Train - Neurons update their connect weight values (learning!)
  • Simplify training method, use basic stochastic gradient descent
  • Add training method or Trainer class
  • Standardize Data set shape for training