Project

Milestone 04: Modeling, Tuning and Visualizing.

The Modeling

Continue exploring and implementing models and strategies for processing, understanding, visualizing your data.

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?

By the end of this milestone you should have some experiments with models that extract non-trivial information from your data. Maybe this model will be used for doing some kind of prediction or classification, or maybe it will be used for creating, modifying or editing data at a later step.

The Tuning

What are the parameters for the model ? Are there variations that can be explored ? Would the model work with 10x as much data? Would it work with fewer data samples ?

Explore some of the parameters for the model and pre-processing functions to see how that affects the results of your analyses.

The Visualizing

How can you tell whether the modeling is working ? Do you have an evaluation strategy ? Is it mathematical or visual ?

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 the previous Milestones.

By now you should have a notebook with your data and modeling exploration as well. Use the same notebook or create a new one to start refining your experiments and collecting results.

Submit a link to this repository through Brightspace.

Future Deadlines

• Milestone 05 - 2024/12/17: Final Presentation and Discussion