Deep Learning In Python - Week 1

An introduction to Python can be seen here:
Python for R users

Steps for Completing the Assignment

Step 1

This week, you can work on the programming assignment on kaggle: https://www.kaggle.com/code/datasniffer/perceptrons-mlp-s-and-gradient-descent

Step 2:

After you're done with the Python tasks in that notebook, clone this github repository onto your laptop via a terminal, or use google colab, or kaggle...anywhere where you can edit python code. There are plenty of online resources which demo how to clone a repo e.g. here: https://www.earthdatascience.org/workshops/intro-version-control-git/basic-git-commands.

Step 3:

• Add the notebook to the repository (download it from Kaggle or Colab or wherever you edited it).
• Then add the requested code to the task.py file (see that file for specifics). You can simply copy-paste your function definitions from the Jupyter notebook into the tasks.py file.

Check under Actions on GitHub to see how many points you received. You can also run the grading files to preview whether your solution passes, but you are not allowed to change these files.

Step 4:

Also add this week's kaggle certificate to the repository (https://www.kaggle.com/learn/intro-to-deep-learning). Name the file certificate.pdf

Step 5:

Push your changes to the repo back to github. The grading will occur automatically but might take a minute. If you have questions or problems, make sure to come to the tutorial on Friday!

Again, the add/commit/push workflow of github is explained in various places online: https://www.earthdatascience.org/workshops/intro-version-control-git/basic-git-commands)