build a simple network to make predictions of bike-sharing usage
build a network for sentiment analysis on the movie review data
Object_Recognition.ipynb
: build a neural network classify images from the CIFAR-10 dataset- Digit_Recognition: build a neural network that recognizes handwritten numbers using the MNIST data set
- Intro_to_RNN: build a character-wise RNN trained on Anna Karenina
- How-to-Generate-Music-Demo: uses Keras & Theano to generate jazz music
train a network to learn representations for words that show up in similar contexts
generate a new TV script for a scene at Moe's Tavern
take a pre-trained neural network (e.g AlexNet, VGG, GoogLeNet, ResNet) and adapting the neural network to a new, different data set
language_translation.ipynb
: build a chatbot that translates text in real time- sequence_to_sequence: build a model that takes in a sequence of letters, and outputs a sorted version of that sequence
- How_to_make_a_chatbot
- How_to_make_a_language_translator
Q-learning-cart.ipynb
: use Q-learning to train an agent to play a game called Cart-Pole- Smartcab: implement a Q-Learning algorithm for the self-driving agent to guide the agent towards its destination within the allotted time
Intro_to_GANs.ipynb
: build a generative adversarial network (GAN) trained on the MNIST dataset- Autoencoders: build a simple autoencoder to compress the MNIST dataset
- Deep_Convolutiona_GANs: implement the Deep Convolutional GAN model to generate full color images
- Generate_Faces: use a generative adversarial network (GAN) to generate novel faces
- How_to_generate_video
- How-to-Learn-from-Little-Data: use a Memory Augmented Neural Network in Tensorflow to perform one-shot learning on the Omniglot dataset
contains code examples for the course CS 20SI: TensorFlow for Deep Learning Research