powstik
Prove
LiveProof-of-Work · Oct–Nov: every verified proof counts. 35 days leftAll outcomes
Skills

Learn Machine Learning Basics

13 weeks · 2 milestones

Machine Learning (Google Machine Learning Crash Course), then one project of your own. Part of the Varsity Curriculum: Computer Science.

Milestone map

Milestone map

2 milestones

Do the course work in public

6–11 weeks (9 hrs/week)

Take Machine Learning for free and do the course exercises (regression, classification, overfitting), in a notebook. Keep everything in one public repo or notebook as you go. OSSU lists the DeepLearning.AI course on Coursera. We use Google's free crash course and Kaggle Learn.

Proof required

Link your public repo or notebook with the course exercises (regression, classification, overfitting), in a notebook, and a screenshot or log showing the self-check passed.

What gets checked

  • Each exercise runs top to bottom.
  • Train and test data are kept apart.
  • Results are explained in plain words.

Common mistakes

  • Copying posted answers: verifiers read the history.
  • Skipping the self-check, then asking for review too early.

Powstik Guide

A public repo or notebook with the course exercises (regression, classification, overfitting), in a notebook.

Steps

  1. Make a public repo or notebook first.
  2. Do one unit at a time and commit after each.
  3. Run the self-check: Finish the exercises; Kaggle checks each one.
  4. Write a short README: what is here and how to run it.
  5. Ask three people who know the topic to check it.

Template

README
Course: Machine Learning (Google Machine Learning Crash Course)
What is here:
How to run it:
Self-check result:
What was hardest:

What gets sent back

  • No history, just one big upload.
  • Self-check not shown.
  • Code that does not run from the README.

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • Each exercise runs top to bottom.
  • Train and test data are kept apart.
  • Results are explained in plain words.
  • Ask one question about a choice in the code; the answer should be clear.

You'll sign in first, then come straight back here.

Train a model on real data

1–3 weeks (5–8 hrs/week)

Use what you learned. Make a model trained on a real public dataset, compared with a simple baseline. Keep it small enough to finish in about two weeks.

Proof required

Link a model trained on a real public dataset, compared with a simple baseline, with a README that says how to run or read it.

What gets checked

  • It beats the baseline on held-out data.
  • The data source and its limits are named.
  • Others can rerun it.

Common mistakes

  • A project too big to finish.
  • A demo that only works on your machine.

Powstik Guide

A model trained on a real public dataset, compared with a simple baseline.

Steps

  1. Write one line: what it does and for whom.
  2. Build the smallest version that works.
  3. Test it on someone else's machine or with someone else reading it.
  4. Write the README.
  5. Ask three people to check it.

Template

README
What it does:
Who it is for:
How to run it:
What I would do next:

What gets sent back

  • Does not run from the README.
  • Not clearly the person's own work.
  • Claims more than it does.

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • It beats the baseline on held-out data.
  • The data source and its limits are named.
  • Others can rerun it.
  • Check that the work is the person's own.

You'll sign in first, then come straight back here.

Part of