← all repositories
udacity/deep-learning

Deep learning by notebook: from NumPy to GANs

Udacity open-sourced its Deep Learning Nanodegree notebooks so you can implement CNNs, RNNs, and GANs without enrolling.

4.1k stars Jupyter Notebook Learning
deep-learning
Not currently ranked — collecting fresh signals.
star history

What it does

This repository holds the tutorial and project notebooks for Udacity’s Deep Learning Nanodegree Foundation program. It is a structured curriculum in Jupyter form, walking through implementations of convolutional networks, recurrent networks, GANs, and supporting techniques like batch normalization and weight initialization. The projects cover the usual suspects: CIFAR-10 classification, Simpsons script generation, and face generation with DCGANs.

The interesting bit

The value is the breadth and the deliberate progression. You begin with sentiment analysis in pure NumPy—no framework magic—and advance through TensorFlow, transfer learning with VGGNet, sequence-to-sequence models, and deep Q-learning. Finding that complete arc from hand-rolled math to high-level libraries in one coherent repo is unusual.

Key highlights

  • Covers the full DL stack: NumPy scratch implementations, TensorFlow, and TFLearn abstractions
  • Includes project notebooks for CIFAR-10 CNNs, Simpsons text generation, English-to-French translation, and CelebA face generation
  • Dependencies are scoped per directory, so you only install what the specific notebook needs
  • Conda environment files are provided, with GPU-labeled variants for TensorFlow

Verdict

Worth bookmarking if you want a guided, breadth-first survey of deep learning fundamentals. Skip it if you are looking for a reusable library rather than coursework.

Frequently asked

What is udacity/deep-learning?
Udacity open-sourced its Deep Learning Nanodegree notebooks so you can implement CNNs, RNNs, and GANs without enrolling.
Is deep-learning open source?
Yes — udacity/deep-learning is open source, released under the MIT license.
What language is deep-learning written in?
udacity/deep-learning is primarily written in Jupyter Notebook.
How popular is deep-learning?
udacity/deep-learning has 4.1k stars on GitHub.
Where can I find deep-learning?
udacity/deep-learning is on GitHub at https://github.com/udacity/deep-learning.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.