daviddoji/vanilla-machine-learning

Go to file

ritchie c7d6fea511 fixed reward function -> less deflection is rewarding

2017-12-16 15:26:44 +01:00

linear_regression

policy network openai gym flagpole

2017-10-31 22:30:20 +01:00

logistic_regression

log regression formula update

2017-11-15 13:26:45 +01:00

reinforcement_learning

fixed reward function -> less deflection is rewarding

2017-12-16 15:26:44 +01:00

.gitignore

first

2017-06-24 21:13:41 +02:00

functions.py

readme

2017-09-03 12:50:43 +02:00

readme.md

readme

2017-09-03 12:50:43 +02:00

simple_mlp.py

learning for both nn working

2017-07-01 12:01:07 +02:00

vanilla_logistic_regression.py

logistic regression

2017-09-10 13:54:17 +02:00

vanilla_mlp.py

vanilla_mlp

2017-07-13 11:28:12 +02:00

readme.md

How to program a neural net from scratch in Python

Read more in this blog post