Talk
- Talk given on 9/20/2018 at Inside Data Konstanz
Notebooks
The easiest to interactively work with the notebooks, is to use google colab (you will need to have a google account for that). In colab the notebook will be run in the cloud. For doing the hands-on part on your own computer you can either install anaconda or use the provided a docker container (you need no google account). See https://tensorchiefs.github.io/dl_course_2018/ for details.
Tasks / Exercises
-
Ninja track (very few hints) linear_regression_tf: notebook static or notebook interactive in colab
-
Yellow belt (some hints) linear_regression_tf: notebook static or notebook interactive in colab
If there is time left, you may want to have a look at the solution for linear regression with TensorFlow eager (see below)
Solutions
Please try it first on your own
-
Linear Regression with TensorFlow (standard graph based): notebook static or notebook interactive in colab
-
Linear Regression with TensorFlow eager: notebook static or notebook interactive in colab
Further material on deep learning, can be found at tensorchiefs $F^{\mu,\nu}$