# Ramakm/ai-hands-on

A group of notebooks  and other files which can help you learn AI from scratch.

Repository: https://github.com/Ramakm/ai-hands-on
Canonical: https://ross.abutalabs.com/products/ai-hands-on
Homepage: https://growtechie.substack.com/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: ai, artificial-intelligence, books, chatbot, machine-learning, math, ml, mlmodel, neural-network, ocr, pytorch, rag, transformer
Last push: 2026-08-17T18:34:14+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 20
- inputs: {"age_days": 282, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1432, forks 301 (observed 2026-08-28T04:04:43.068524+00:00)

## What it is
A collection of Jupyter notebooks and supporting files that teach AI engineering from first principles, covering math, PyTorch, neural networks, transformers, RAG, and OCR. It is a structured, hands-on curriculum for beginners and engineers levelling up in AI.

## Use cases
- learn AI from scratch with guided notebooks
- build neural networks from first principles in PyTorch
- understand transformer and attention mechanisms
- build an end-to-end RAG pipeline with embeddings and vector stores
- learn OCR image preprocessing and text extraction
- review math fundamentals like linear algebra and gradients for ML
- follow a structured path to become an AI engineer

## When to choose
- you want a free, notebook-driven curriculum covering math through LLM systems
- you prefer learning by building neural networks and RAG pipelines from scratch
- you are a beginner or engineer transitioning into AI engineering

## When to avoid
- you need production-ready AI libraries or frameworks rather than learning material
- you want a comprehensive course with graded exercises and certification
- you need non-PyTorch frameworks like TensorFlow or JAX examples

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, rag, ocr, nlp
- domain: artificial-intelligence, machine-learning, deep-learning, large-language-models, education, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, pytorch, transformers, neural-networks, math-fundamentals, hands-on-learning, ai-engineering

## Member repositories
- Ramakm/ai-hands-on (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.068524+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:00.418717+00:00, confidence not recorded.
  - readme: https://github.com/Ramakm/ai-hands-on (fetched 2026-08-28T04:04:43.068524+00:00, sha bc2a6e474096)
  - homepage: https://growtechie.substack.com/ (fetched 2026-08-29T11:48:09.915510+00:00, sha c4c302079e25)
- Data as of 2026-08-30T08:39:29.467469+00:00.