Milestone map
Milestone map
2 milestones
Do the course work in public
2–3 weeks (10 hrs/week)
Take Unsupervised Learning, Recommenders, Reinforcement Learning for free and do the 6.036 homework for clustering, recommender systems, Markov decision processes and reinforcement learning, with your code in a public repo. Keep everything in one public repo or notebook as you go. OSSU lists a DeepLearning.AI course on Coursera, where graded work is paid. We use the free MIT 6.036 units on the same topics.
Proof required
Link your public repo or notebook with the 6.036 homework for clustering, recommender systems, Markov decision processes and reinforcement learning, with your code in a public repo, and a screenshot or log showing the self-check passed.
What gets checked
- The site shows the exercises answered correctly.
- Your code reproduces the homework numbers.
- Each unit has a short note in your own 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 6.036 homework for clustering, recommender systems, Markov decision processes and reinforcement learning, with your code in a public repo.
Steps
- Make a public repo or notebook first.
- Do one unit at a time and commit after each.
- Run the self-check: Do the exercises and homework for the units on clustering, recommender systems, Markov decision processes and reinforcement learning; the site checks each answer.
- Write a short README: what is here and how to run it.
- Ask three people who know the topic to check it.
Template
README Course: Unsupervised Learning, Recommenders, Reinforcement Learning (MIT 6.036 Introduction to Machine Learning (Open Learning Library)) 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
- The site shows the exercises answered correctly.
- Your code reproduces the homework numbers.
- Each unit has a short note in your own 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.
Build a small recommender or agent
1–3 weeks (5–8 hrs/week)
Use what you learned. Make a recommender on a real ratings dataset, or a learning agent for a simple game, with a measure of how well it does. Keep it small enough to finish in about two weeks.
Proof required
Link a recommender on a real ratings dataset, or a learning agent for a simple game, with a measure of how well it does, with a README that says how to run or read it.
What gets checked
- It beats a simple baseline (most popular items, or random moves).
- The measure is stated and fair.
- It runs from the README.
Common mistakes
- A project too big to finish.
- A demo that only works on your machine.
Powstik Guide
A recommender on a real ratings dataset, or a learning agent for a simple game, with a measure of how well it does.
Steps
- Write one line: what it does and for whom.
- Build the smallest version that works.
- Test it on someone else's machine or with someone else reading it.
- Write the README.
- 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 a simple baseline (most popular items, or random moves).
- The measure is stated and fair.
- It runs from the README.
- Check that the work is the person's own.
You'll sign in first, then come straight back here.