# GoogleCloudPlatform/tensorflow-without-a-phd

A crash course in six episodes for software developers who want to become machine learning practitioners.

Repository: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd
Canonical: https://ross.abutalabs.com/products/tensorflow-without-a-phd
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-05-03T05:16:18+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3038, "days_push": 852, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2851, forks 909 (observed 2026-08-28T04:07:25.663542+00:00)

## What it is
A six-episode crash course with Jupyter Notebook code samples, videos, slides, and codelabs teaching software developers deep learning with TensorFlow. It covers neural network basics, training best practices, and convolutional networks through hands-on examples like MNIST digit recognition.

## Use cases
- learn machine learning as a software developer
- understand neural networks without a math PhD
- train a CNN on MNIST handwritten digits
- learn TensorFlow training best practices like dropout and batch normalization
- find hands-on deep learning codelabs and notebooks
- transition from software engineering to ML practice

## When to choose
- you are a developer new to machine learning wanting a structured video-plus-code course
- you prefer learning through runnable Jupyter Notebook examples
- you want practical training tips like learning rate decay and regularization

## When to avoid
- you need up-to-date TensorFlow 2.x or PyTorch content, as the material is dated
- you are an experienced ML practitioner seeking advanced topics
- you need maintained production code rather than educational samples

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools
- domain: machine-learning, deep-learning, tutorials, education
- platform: python, cross-platform
- tags: tensorflow, jupyter-notebooks, tutorial-series, neural-networks, google-cloud

## Member repositories
- GoogleCloudPlatform/tensorflow-without-a-phd (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:25.663542+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 2026-08-30T07:36:53.403016+00:00, confidence not recorded.
  - readme: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd (fetched 2026-08-28T04:07:25.663542+00:00, sha 07317e46083e)
- Data as of 2026-08-30T08:39:29.467469+00:00.