Some exercises with Image Neural Networks

1. Use the HW12 template to start a repository in your organization’s GitHub space. It should be named HW10. Open the notebook file using GitHub Codespaces to continue the exercises.

2. Complete the exercises and answer the interpretation questions in the notebook.

3. Submit a link to your repository with the completed exercises using Brightspace.

Project

Milestone 03: Data Exploration and Preliminary Modeling

The Data

Continue fixing, pre-processing and preparing the data for your project.

By the end of this milestone you should have a pretty solid grasp of the data that you’re working with, and it should be going into DataFrame or Tensor objects without errors about missing data or NaN values.

The Graphs

Visualize your data. You should have some graphs and statistics about the distribution of your data and its features.

Do cluster graphs give you any meaningful insight into the data? Does PCA?

If working with audio, image or other media files, you should have some color histograms or FFT plots.

The Model

What kind of modeling are you using? Is it regression, classification, generative or something else for exploration/visualization?

Are you using some of the classic models from scikit-learn, or something with Neural Networks and PyTorch? Is it something very different from what we saw in class?

Submission

Document your research, any new ideas and write a description of your data in your Project repository on GitHub. Use the same repository as Milestones 01 and 02.

If you didn’t have one before, create a notebook for doing data exploration and include that in the repository as well. Use the same notebook or create a new one to start doing experimental modeling with the data.

Submit a link to this repository through Brightspace.

Future Milestones

• Milestone 04 - 2024/12/10: Tuning and Adjusting.
• Milestone 05 - 2024/12/17: Final Presentation and Discussion