# DorsaRoh/Machine-Learning

ML from scratch

Repository: https://github.com/DorsaRoh/Machine-Learning
Canonical: https://ross.abutalabs.com/products/dorsaroh-machine-learning
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: machine-learning
Last push: 2025-08-12T22:15:36+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 36, release rhythm 35, longevity 54
- inputs: {"age_days": 762, "days_push": 386, "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 2447, forks 194 (observed 2026-08-28T04:06:52.749831+00:00)

## What it is
A collection of Jupyter Notebook tutorials implementing machine learning models from scratch using only NumPy. It covers neural networks, transformers, and distributed models with detailed explanations of the underlying math and code.

## Use cases
- learn how neural networks work internally
- implement a neural network from scratch with numpy
- understand forward and backpropagation step by step
- build a transformer without frameworks
- study machine learning fundamentals with runnable notebooks
- see how weights, biases, and activation functions work

## When to choose
- you want to deeply understand ML internals rather than use a high-level framework
- you prefer minimal dependencies like NumPy only
- you learn best from annotated, executable notebooks

## When to avoid
- you need production-ready, optimized training code
- you want GPU acceleration or distributed training at scale
- you need a maintained library API rather than educational material

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning, education, tutorials
- platform: python
- tags: from-scratch, numpy, jupyter-notebooks, neural-networks, transformer, educational

## Member repositories
- DorsaRoh/Machine-Learning (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:52.749831+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 2026-08-30T02:30:30.461898+00:00, confidence not recorded.
  - readme: https://github.com/DorsaRoh/Machine-Learning (fetched 2026-08-28T04:06:52.749831+00:00, sha 2847b8a4563a)
- Data as of 2026-08-30T08:39:29.467469+00:00.