https://github.com/tarrysingh/artificial-intelligence-deep-learning-machine-learning-tutorials
Synapsa Commons: free, hands-on AI courses that run anywhere (Colab, Kaggle, Binder, Codespaces, Jupyter). EU AI Act conformity evidence, model validation, predictive maintenance, document extraction, retrieval and RAG, AI agents and MCP, a simulated humanoid. Every lesson autograded. From the team building Synapsa.
https://github.com/tarrysingh/artificial-intelligence-deep-learning-machine-learning-tutorials
ai-agents ai-governance artificial-intelligence autograding deep-learning document-ai eu-ai-act google-colab humanoid-robotics jupyter-notebook machine-learning mlops model-risk-management mujoco online-course predictive-maintenance python rag responsible-ai synapsa
Last synced: 1 day ago
JSON representation
Synapsa Commons: free, hands-on AI courses that run anywhere (Colab, Kaggle, Binder, Codespaces, Jupyter). EU AI Act conformity evidence, model validation, predictive maintenance, document extraction, retrieval and RAG, AI agents and MCP, a simulated humanoid. Every lesson autograded. From the team building Synapsa.
- Host: GitHub
- URL: https://github.com/tarrysingh/artificial-intelligence-deep-learning-machine-learning-tutorials
- Owner: TarrySingh
- License: other
- Created: 2017-07-13T19:46:01.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2026-11-10T12:12:46.000Z (12 days ago)
- Last Synced: 2026-11-14T21:37:17.824Z (8 days ago)
- Topics: ai-agents, ai-governance, artificial-intelligence, autograding, deep-learning, document-ai, eu-ai-act, google-colab, humanoid-robotics, jupyter-notebook, machine-learning, mlops, model-risk-management, mujoco, online-course, predictive-maintenance, python, rag, responsible-ai, synapsa
- Language: Python
- Homepage: https://synapsa.realai.eu
- Size: 18.4 MB
- Stars: 4,026
- Watchers: 297
- Forks: 1,619
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Notice: NOTICE
Awesome Lists containing this project
README
**Free, hands-on AI courses that run anywhere, from the team building Synapsa, an AI-native
learning platform.**
[](https://github.com/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/actions/workflows/lessons.yml)
Every lesson here is a notebook you *do*, not one you read. You fill in the exercises, and each one
checks itself the moment you run it. Hints stay hidden until you ask for them. Worked solutions
and the full autograded rubric, with partial credit and an official score, come with free
enrolment on [Synapsa](https://synapsa.realai.eu), opening in the coming weeks. Some lessons are C or C++ exercises, built and graded the same way. Open any of them in
Google Colab, Kaggle, Binder, GitHub Codespaces or your own Jupyter: the first cell installs what the
lesson needs at the versions it was measured with, and does nothing where it is already there.
The courses are aimed at the work people are actually paid for: evidence an inspector can re-run, a model
a risk committee can sign off, an alarm a plant manager will trust. Every number a lesson prints is
computed by code you run, and every claim it makes about the world cites a primary source.
## Where to start
| If you want to… | Course | First lesson |
|---|---|---|
| Show that an AI system meets the EU AI Act, with evidence an inspector can re-run | [`programmes/ai-act-conformity/`](programmes/ai-act-conformity/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T10-L01-ai-act-conformity-pack/lesson.ipynb) |
| Validate a model well enough to sign it off: calibration, challengers, explainability, the committee pack | [`programmes/model-risk/`](programmes/model-risk/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/programmes/model-risk/lessons/P04-L01-validation-suite/lesson.ipynb) |
| Take predictive maintenance from sensor physics to an alarm threshold priced in money | [`programmes/predictive-maintenance/`](programmes/predictive-maintenance/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/programmes/predictive-maintenance/lessons/P03-L01-alarm-economics/lesson.ipynb) |
| Pull fields out of invoices and contracts, and prove how often you are wrong | [`programmes/document-intelligence/`](programmes/document-intelligence/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/programmes/document-intelligence/lessons/P02-L01-extraction-evaluation/lesson.ipynb) |
| Build credit models that survive an audit: vintage curves, a hazard model, macro scenarios and an out-of-time back-test | [`programmes/credit-underwriting/`](programmes/credit-underwriting/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/programmes/credit-underwriting/lessons/P05-L01-pd-vintages-and-macro/lesson.ipynb) |
| Get from mass spectra to proteins you can defend: a search engine, target-decoy FDR, protein inference, missing values and batch effects | [`programmes/proteomics-multiomics/`](programmes/proteomics-multiomics/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/programmes/proteomics-multiomics/lessons/P07-L01-search-engine-and-fdr/lesson.ipynb) |
| Make a simulated humanoid stand and walk, then measure how far that is from a robot | [`flagships/humanoid-lab/`](flagships/humanoid-lab/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/flagships/humanoid-lab/lessons/F15-L01-first-contact/lesson.ipynb) |
| Build search and RAG you can measure: retrieval, chunking, the context budget, reranking and agent memory | [`lessons/`](lessons/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T06-L01-retrieval-from-scratch/lesson.ipynb) |
| Build AI agents that hold up: the agent loop from scratch, MCP and A2A from the wire up, evaluation, observability and constrained decoding | [`lessons/`](lessons/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T07-L01-agent-loop-from-scratch/lesson.ipynb) |
| Do AI for science on real data: find the first gravitational wave in the raw LIGO data, and model rainfall to runoff honestly | [`lessons/`](lessons/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T12-L01-find-gw150914/lesson.ipynb) |
| Serve and train language models on modest hardware: a KV cache, paging and continuous batching on a CPU, and GRPO from scratch | [`lessons/`](lessons/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T05-L01-serving-on-a-cpu/lesson.ipynb) |
| Start from nothing: the 8 GB machine, tokenisers from scratch, a language model on a CPU | [`lessons/`](lessons/) | [Colab](https://colab.research.google.com/github/TarrySingh/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/blob/master/lessons/T00-L01-the-8gb-track/lesson.ipynb) |
The model-risk, predictive-maintenance, document-intelligence, credit and proteomics courses build
on [`lessons/T00-L01-the-8gb-track`](lessons/T00-L01-the-8gb-track/), which makes the profiler and the
compute tiers every lesson is held to; start there if you have not done it. Each programme's
`MODULES.md` is its map and shows which lessons exist and which are still only specified; the
humanoid lab's is its `README.md`, and [`lessons/`](lessons/) has its own.
## What exists today
**74 lessons, every one passing all 14 gates in `QUALITY.md` and independently reviewed.** 7 are compiled C or C++ exercises. Every notebook opens in Colab, Kaggle, Binder, Codespaces or local Jupyter. Every `MODULES.md` marks a module built only when its lesson exists and has passed; everything else says `specified`, and means it.
| Area | Built | Specified, not built |
|---|---|---|
| `flagships/humanoid-lab` | 8 lessons + capstone | — |
| `lessons/` — track lessons | 24 | — |
| `programmes/ai-act-conformity` | 9 of 9 | 0 |
| `programmes/credit-underwriting` | 1 of 8 | 7 |
| `programmes/document-intelligence` | 11 of 11 | 0 |
| `programmes/model-risk` | 10 of 10 | 0 |
| `programmes/predictive-maintenance` | 9 of 9 | 0 |
| `programmes/proteomics-multiomics` | 2 of 7 | 5 |
## What's coming
New lessons three times a week, every Monday, Wednesday and Friday. Watch or star this repository to hear about each one as it lands.
```mermaid
timeline
September 2026 : Document intelligence for regulated operations, retrieval and RAG, and the agents track begins
October 2026 : AI agents and the protocols they speak, two new industry programmes on proteomics and multiomics and on evidence-based credit decisions, AI for science, serving models on modest hardware, post-training from scratch, and evaluating across languages
November 2026 : The credit decisions and the proteomics and multiomics programmes continue, module by module
December 2026 : Deeper courses in the industries we already cover
```
## How a lesson works
Press **Run all** before you have written a line. Every cell still runs: each unfinished exercise
says it is not implemented yet, and the notebook ends with a progress board, one line per exercise,
marked ✅ passed, ❌ failed or ⏳ not started. Fill in an exercise and re-run its cell, and its check
tells you whether you are right, and if not, what the likely mistake is. Each exercise has two
hints: the first says what to think about, the second the approach in words. Neither gives you the
answer. Your score against the full rubric, and the worked solution, come with enrolment on
Synapsa.
Anything a lesson measures on your machine, like a time or a memory peak, prints with its unit and
will differ from ours. Every other number a finished lesson prints is identical on Python 3.11 and
3.12; every lesson is checked for that before it is released. The workflow above checks on Linux,
which is what Colab, Kaggle, Binder and Codespaces run, that every notebook opens and runs.
On Kaggle, a lesson that installs a package or fetches a file needs Internet switched on in the
notebook's settings, and Kaggle allows that only for phone-verified accounts. Colab, Binder and
Codespaces need nothing.
To work locally instead, with Python 3.11 or 3.12:
python -m venv .venv && .venv/bin/pip install -r requirements.txt
.venv/bin/jupyter lab
On Windows the two commands are `.venv\Scripts\pip` and `.venv\Scripts\jupyter`.
## The bar every lesson clears
[`QUALITY.md`](QUALITY.md) sets out 14 gates. The short version:
- measurable objectives, and prerequisites that are real lessons;
- scaffolded exercises with instant feedback, an autograded rubric, a worked solution and a
self-check;
- runs top to bottom in a fresh interpreter, inside a declared compute tier and time budget;
- data that is free and needs no registration, named with its licence;
- every claim about the world cites a primary source, and no measured or computed number in the
prose is typed by hand;
- the notebook opens and runs alone on Python 3.11 and 3.12, and Run all is a good experience.
A lesson is marked built only after an independent reviewer has tried to break it, including by
grading plausible wrong answers against its rubric.
## For maintainers
- `lessons/`, `flagships/`, `programmes/`: track lessons, flagship subtrees, industry programmes.
- Lessons are written and gated in a separate source that holds the worked solutions and the
rubrics; this repository receives the student version of each lesson once it passes.
- `tools/notebooks.py` generates each `lesson.ipynb` and its launcher cell (`--check` for drift),
and `tools/verify_portable.py` runs each notebook alone in a minimal kernel on Python 3.11 and
3.12. `.github/workflows/lessons.yml` runs both on Linux on every change, and fails if a
solution or rubric file is ever committed here.
- `brand/` holds the Synapsa Commons lockups used here and at the top of every notebook.
## The 2017-2025 tutorials
From 2017 to 2025 this repository carried a curated collection of machine-learning and
deep-learning tutorials, much of it gathered from other people's work. It helped a great many
learners, and we are grateful to everyone who starred it, forked it and contributed to it. That
collection has now been retired from public view, so that everything published here is original
work we can stand behind and license. Synapsa Commons replaces it.
## Licence
Synapsa Commons is © 2026 RealAI, free to learn from and share, and licensed under
[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/); the legal code is in
[`LICENSE`](LICENSE) and a plain-words summary in [`NOTICE`](NOTICE).
| You may | You must | You may not |
|---|---|---|
| use the lessons to learn and to teach; copy, fork, share and adapt them | credit "Synapsa Commons by RealAI" with a link here, say what you changed, and share adaptations under the same licence | use them, or anything adapted from them, for commercial advantage or payment: selling them, charging for a course or training built on them, or packaging them into a paid product or service |
Commercial licences are available from [RealAI](https://www.realai.eu/contact). Third-party
material inside a lesson keeps its own licence, named in that lesson's `assets/SOURCE.md` or
`claims.yaml`. The Synapsa name and logo belong to RealAI and are not licensed.