Repo for the Deep Learning Nanodegree Foundations program.
Clone or download
fixingitnow docs: updated documentation inside the Jupyter notebook.
The code was contradicting the statements, so updated the statements.
Latest commit 05dbe41 Sep 12, 2018
Failed to load latest commit information.
IMDB-keras Adding notebooks for DLND Nov 14, 2017
autoencoder stride reduces the size by a factor Jul 20, 2017
batch-norm docs: updated documentation inside the Jupyter notebook. Sep 12, 2018
dcgan-svhn correct dcgan coding practice issue Mar 28, 2018
embeddings Update Skip-Gram_word2vec.ipynb Jul 4, 2017
environments Fix tornado version in Mac environments Apr 25, 2017
face_generation fix typo Mar 20, 2018
first-neural-network add autoreload for external modules for P1 Feb 12, 2018
gan_mnist fix typo Feb 21, 2018
gradient-descent Adding notebooks for DLND Nov 14, 2017
image-classification Edit README and project notebook for new FloydHub dataset Aug 24, 2017
intro-to-rnns Add print control for training loss Jan 3, 2018
intro-to-tensorflow fixed solutions github url Apr 27, 2017
intro-to-tflearn Fix `trainY` and `testY` Jun 12, 2017
language-translation Merge pull request #134 from JackBurdick/patch-1 Jul 21, 2017
linear-regression Changing learning rate. Nov 20, 2017
reinforcement Remove training output from notebooks to make the files smaller. May 29, 2017
semi-supervised Add semi-supervised notebooks Jun 1, 2017
sentiment-network Simplify log ratios in Trask notebooks May 19, 2017
sentiment-rnn Fix typo. Feb 18, 2018
seq2seq Fix dynamic_decode function to work with TensorFlow 1.2 Jul 21, 2017
student-admissions-keras fix typo Apr 3, 2018
student-admissions Adding notebooks for DLND Nov 14, 2017
tensorboard Remove spaces from filenames Apr 14, 2017
transfer-learning don't ask to clone machrisaa/tensorflow-vgg Jul 22, 2017
tv-script-generation Make compatible with TensorFlow 1.3 and later Mar 23, 2018
weight-initialization add dependencies for weight initialization lesson. Apr 1, 2017
.gitignore Merge branch 'master' into patch-1 Jun 14, 2017
.gitmodules Add gym as submodule Apr 14, 2017
LICENSE Add LICENSE file Apr 3, 2017 Flesh out README May 29, 2017

Deep Learning Nanodegree Foundation

This repository contains material related to Udacity's Deep Learning Nanodegree Foundation program. It consists of a bunch of tutorial notebooks for various deep learning topics. In most cases, the notebooks lead you through implementing models such as convolutional networks, recurrent networks, and GANs. There are other topics covered such as weight intialization and batch normalization.

There are also notebooks used as projects for the Nanodegree program. In the program itself, the projects are reviewed by Udacity experts, but they are available here as well.

Table Of Contents



  • Your First Neural Network: Implement a neural network in Numpy to predict bike rentals.
  • Image classification: Build a convolutional neural network with TensorFlow to classify CIFAR-10 images.
  • Text Generation: Train a recurrent neural network on scripts from The Simpson's (copyright Fox) to generate new scripts.
  • Machine Translation: Train a sequence to sequence network for English to French translation (on a simple dataset)
  • Face Generation: Use a DCGAN on the CelebA dataset to generate images of novel and realistic human faces.


Each directory has a requirements.txt describing the minimal dependencies required to run the notebooks in that directory.


To install these dependencies with pip, you can issue pip3 install -r requirements.txt.

Conda Environments

You can find Conda environment files for the Deep Learning program in the environments folder. Note that environment files are platform dependent. Versions with tensorflow-gpu are labeled in the filename with "GPU".