Skip to content

Week 5

hackmd-github-sync-badge](https://hackmd.io/BEx2SHHWQXGvtj-9WBlGTA)

In this lesson you will create a batch machine-learning workflow using deep learning examples from Deep Learning with Python. This workflow should be similar to real-world machine-learning workflows that you may encounter in professional or personal projects.

Objectives

After completing this week, you should be able to:

  • Create deep learning models that perform machine learning tasks including binary classification, multi-label classification, and regression
  • Create workflows that train deep learning models and then produce validation and metrics on those models

Readings

  • Read chapters 3 and 4 Deep Learning with Python

Weekly Resources

Assignment 5

In this assignment, you will be reproducing the models described in the examples from chapter three of Deep Learning with Python. You will use that code to create a workflow that trains the model, uses the model to perform model validation, and output model metrics.

Assignment 5.1

Implement the movie review classifier found in section 3.4 of Deep Learning with Python.

Assignment 5.2

Implement the news classifier found in section 3.5 of Deep Learning with Python.

Assignment 5.3

Implement the housing price regression model found in section 3.6 of Deep Learning with Python.

Submission Instructions

For this assignment, you will submit a zip archive containing the contents of the dsc650/assignments/assignment05/ directory. Use the naming convention of assignment05_LastnameFirstname.zip for the zip archive.

If you are using Jupyter, you can create a zip archive by running the Package Assignments.ipynb notebook.

You can create this archive in Bash (or a similar Unix shell) using the following commands. 

cd dsc650/assignments
zip -r assignment05_DoeJane.zip assignment05

Likewise, you can create a zip archive using Windows PowerShell with the following command. 

Compress-Archive -Path assignment05 -DestinationPath 'assignment05_DoeJane.zip

Discussion Board

You are required to have a minimum of 10 posts each week. Similar to previous courses, any topic counts towards your discussion count, as long as you are active more than 2 days per week with 10 posts, you will receive full credit. Refer to the optional topic below as a starting place.

Post about how you would implement a similar deep learning workflow for a use case that is applicable to your professional or personal interests. In this use case, how often would you need to train the models? How would you deploy the models?

Last update: March 12, 2023