# dreddnafious/thereisnospoon

A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.

Repository: https://github.com/dreddnafious/thereisnospoon
Canonical: https://ross.abutalabs.com/products/thereisnospoon
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, engineering, fundamentals, machine-learning, neural-networks, primer, transformers, tutorial
Last push: 2026-03-29T21:33:57+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 35, longevity 11
- inputs: {"age_days": 157, "days_push": 157, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1184, forks 93 (observed 2026-08-28T04:03:54.814832+00:00)

## What it is
A machine learning primer written from first principles as a single markdown document with inline visualizations. It teaches engineers to reason about ML systems using physical and engineering analogies, covering fundamentals, architectures, and gating mechanisms.

## Use cases
- learn machine learning fundamentals from first principles
- understand how transformers and attention work intuitively
- build a mental model of neural networks as a software engineer
- understand backpropagation and gradient flow intuitively
- learn when to choose which ML architecture for a problem
- get an engineer-friendly introduction to deep learning concepts

## When to choose
- you are a strong software engineer wanting to build intuition for ML rather than memorize math
- you prefer analogy-driven explanations over textbook derivations
- you want a single self-contained readable document covering neurons through transformers

## When to avoid
- you need hands-on code exercises or runnable notebooks
- you want a rigorous mathematical treatment with proofs
- you need a reference for production ML tooling or frameworks

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, developer-tools
- domain: machine-learning, deep-learning, education, tutorials
- platform: python
- tags: primer, first-principles, mental-models, neural-networks, transformers, analogies, markdown-book

## Member repositories
- dreddnafious/thereisnospoon (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.814832+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 2026-08-30T06:24:14.610478+00:00, confidence not recorded.
  - readme: https://github.com/dreddnafious/thereisnospoon (fetched 2026-08-28T04:03:54.814832+00:00, sha dadfd565fe3e)
- Data as of 2026-08-30T08:39:29.467469+00:00.