Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit b27f974

Browse files
Update README.md
1 parent ebf7129 commit b27f974

File tree

1 file changed

+3
-0
lines changed

1 file changed

+3
-0
lines changed

‎README.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,9 @@ These notebooks complement the working paper [Differential Machine Learning](htt
77

88
<a href="https://colab.research.google.com/github/differential-machine-learning/notebooks/blob/master/DifferentialML.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
99

10+
**DifferentialMLTF2.ipynb** is an upgrade to DifferentialML.ipynb for TensorFlow 2.x. Its current form does not run 'idiomatic' TensorFLow 2 code, what we do is really run TensorFlow 1 code in TensorFlow 2. Still, the new notebook benefits from the latest TensorFlow improvements resulting in a noticeable performance improvement. DifferentialML.ipynb will no longer be maintained going forward, bug fixes, improvements and extensions will be implemented directly in the TensorFlow 2 notebook.
11+
12+
<a href="https://colab.research.google.com/github/differential-machine-learning/notebooks/blob/master/DifferentialML.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
1013

1114
**DifferentialRegression.ipynb** applies differential learning in the context of classic regression models. In the article, we applied differential learning to deep neural networks only. This notebook applies it to polynomial regression to the basket option in a correlated Bachelier model of section 3,1. We see that, with regression too, differential training provides a massive performance improvement, without the need for additional regularization, or hyperparameter optimization.
1215

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /