M1
Linear Algebra and Matrix Mechanics for Machine Learning
Vector spaces, matrix representations, and geometric transformations.
00Coming soon · free forever
6 TracksCode + theoryBy students
What’s being written
Change of basis
The normal equations
Rank and nullity
- 6
- Tracks
- 35
- Modules
- 100+
- Problems
- $0
- Forever
01Why this guide
One ordered path
Math, code, classical ML, deep learning, modern AI, then contest practice. Every prerequisite lands before you need it.
Built for the contest
Problems, notebooks, and mock contests written at real USAAIO difficulty, not a generic ML blog.
Free, forever
Made by students, for students. No paywall, no course upsell. Just the path.
02The complete syllabus
Six tracks, foundations through practice. Pick a track to see its modules.
Track 01
Math for AI
The linear algebra, calculus, probability, and optimization every model rests on.
Demo progress3 of 9 complete
3Complete1Practicing1Reading1Skipped3Not Started
M2
Matrix Decompositions for Machine Learning
Factorizing matrices into fundamental components: SVD, eigendecomposition, and friends.
M3
Matrix Calculus for Machine Learning
Gradients, derivatives, and optimization over matrix structures.
M4
Optimization for Machine Learning
Iterative algorithms and frameworks for finding optimal solutions.
M5
Probability for Machine Learning
Uncertainty, random variables, and probability distributions.
M6
Information Theory for Machine Learning
Entropy, information, and statistical divergence.
M7
Probabilistic Models for Machine Learning
Data distributions, variational inference, and generative architectures.
M8
Stochastic Dynamics
Continuous-time processes, differential equations, and dynamic sampling.
Bonus RL
Reinforcement Learning
Sequential decision-making and dynamic programming. Not on the USAAIO syllabus.
Sample progress: try it, saved in this browser only
03Inside the real product
Not screenshots.
The actual interface.
Every panel below is real guide code on sample data. Type in the editor. Run it. Filter the problem set.
01 · Training
- Live typing and epoch log
- Loss curve and accuracy, epoch by epoch
- Starts the moment it scrolls into view
02 · Lessons
- Real Python in the browser, no server
- Derivations stay hidden until you want them
- Quiz answers explain why they are wrong
03 · Problem Set
- Coding and non-coding tasks
- Filter by as many tags as you like
- Real USAAIO tiers and difficulty
04 · Dashboard
- Progress broken down by track
- Six-month activity heatmap
- Pick up exactly where you stopped
05 · Quiz
- Two questions, both from a real module
- Distractors explained, not just marked
- The dissection is one click down
06 · Drill
- Five pieces, five jobs, shuffled
- Wrong pairs bounce back
- Runs entirely in the browser
04Who is behind this
Builtbystudents,forstudents.
We are students preparing for the same contest you are. There was no single place that taught the material in order, so we started writing one as we worked through it. Every module here is something we needed and could not find.
We run it under The OpenGate Network, a 501(c)(3) nonprofit built to keep this kind of teaching free. Nobody is being paid, nothing is being upsold, and there is no tier of the guide you have to buy your way into. If it helps one more person qualify, it has done its job.
Written from the student side
We learn each topic, then write the explanation we wish we had started with. When a derivation loses us, it gets rewritten until it does not.
Shaped in the open
Nothing here is locked away. Spot a rough explanation or a missing step, tell us, and it gets fixed. The guide is shaped by the people working through it.
Still being written
New modules and problem sets go up as we finish them. You will see the guide grow rather than arrive fully formed.
The OpenGate Network · 501(c)(3)
One guide, part of a wider mission.
USAAIO Guide is one initiative of The OpenGate Network, a student-led nonprofit making AI education easier to enter and free to continue. OpenGate connects clear learning paths with the experienced people and honest feedback students need when they get stuck.
Alongside this guide, OpenGate runs a free four-week AI camp for younger students and is building local chapters, student hackathons, research groups, and an open notes library.
You can contribute by teaching or mentoring, writing curriculum, building software, starting a chapter or camp, organizing a hackathon, helping with outreach, or proposing something new. Choose the work that fits you in the contributor form and the team will follow up by email.
Corrections, clearer explanations, and new lessons are welcome from anyone.
05Support the guide
Help sustain the guide.
This guide has never charged for access. That has been possible because our small team has personally funded the hosting, the problem judge and the tooling that keeps the lessons current. That cost is real, and it is growing. A donation helps share it across everyone who uses the guide, rather than leaving it to the team alone, so it stays free for the students who come next.
Frequency
The OpenGate Network is fiscally sponsored by Hack Club, a 501(c)(3) nonprofit. Our registered EIN is 81-2908499, and donations are tax deductible in the US.
Give from your phone
Scan with your phone's camera. Apple Pay or Google Pay can complete it in a tap if your card's already saved.
06Questions
Before you sign up.
Yes. Every lesson, problem, notebook, and tool on the guide is free to use, with no account wall in front of the reading and no paid tier waiting behind it. We are students writing this for other students, so there is nothing to upsell and no plan to change that.
Not yet. We are still writing the first wave of lessons and problems, and we would rather ship something you can work through than a half-finished shell. Join the waitlist and you get one email the day the guide opens. No drip sequence, no weekly digest.
Comfortable high-school algebra is enough to start. The math track builds the linear algebra, calculus, probability, and optimization that later modules assume, and the Python track covers NumPy before you touch real models. If you already know some of that, you can skip ahead; the syllabus is ordered, not gated.
No. USAAIO Guide is an independent, community-built roadmap written by students preparing for the same contest. It is not affiliated with, endorsed by, or officially connected to USAAIO, the IOAI, the IAIO, or the Beaver-Edge AI Institute. For official rules, eligibility, and registration, go to usaaio.org.
No. Most of the Python in the guide runs in your browser through Pyodide, so a normal laptop is enough for the early tracks. Anything that actually needs a GPU (training a small network, running a heavier notebook) opens in Google Colab instead of asking you to set up CUDA locally.
Please do. Join the conversation on our Discord and tell us what felt unclear, which prerequisite was missing, or what kind of problem would have helped a concept click. If you want to contribute directly by writing curriculum, mentoring, building software, organizing a chapter or event, or proposing something new, fill out the OpenGate contributor form. The team will follow up by email.
07Launch email
Get the guide when it opens.
One thoughtful email on launch day. No drip sequence, no weekly digest.