Spandan-Madan/DeepLearningProject resource

Health v2 · maintenance only

Adoption not part of the score

4814 stars · 640 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

An in-depth end-to-end tutorial of a machine learning pipeline, originally built for a Harvard data science class, covering dataset creation, conventional ML, and deep learning. It is available as an HTML page and Jupyter notebooks, with both TensorFlow/Keras and PyTorch versions.

Use cases

• learn the full machine learning pipeline from scratch
• understand how to build your own dataset instead of using MNIST
• compare conventional ML vs deep learning approaches
• learn deep learning with PyTorch through a worked example
• find a weekend-length ML tutorial beyond quick syntax intros
• study model evaluation and implementation decisions in ML

When to choose

• you want a comprehensive, end-to-end walkthrough of a real ML pipeline
• you are a student or practitioner moving beyond toy MNIST tutorials
• you want to learn how to create and use your own dataset
• you prefer learning via Jupyter notebooks with runnable code

When to avoid

• you need a quick 30-minute introduction to neural networks
• you need production-ready or maintained ML code
• you require support for modern Python versions, as the original targets Python 2.7
• you want cutting-edge deep learning techniques

Facets

learning-resource · maturity maintenance

machine-learning deep-learning data-science machine-learning deep-learning data-science tutorials python cross-platform tutorial jupyter-notebook pytorch tensorflow machine-learning-pipeline harvard educational

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Spandan-Madan/DeepLearningProject")