In this repository I will commit my progress toward the Deep Learning Nanodegree Foundation. I will start the four month term on the 14th of November 2017.
The Nanodegree exists of several courses and five projects.
- Project 1 - Your First Neural Network:
- Build and train neural networks from scratch to predict the number of bikeshare users on a given day.
- Project 2 - Dog-Breed Classifier:
- Design and train a convolutional neural network to analyze images of dogs and correctly identify their breeds. Use transfer learning and well-known architectures to improve this model—this is excellent preparation for more advanced applications.
- Project 3 - Generate TV Scripts:
- Build a recurrent neural network on TensorFlow to process text. Use it to generate new episodes of your favorite TV show, based on old scripts.
- Project 4 - Generate Faces:
- Build a pair of Multi-Layer Neural Networks and make them compete against each other in order to generate realistic faces. Try training them on a set of celebrity faces, and see what new faces the computer comes out with!
- Project 5 - Teach a Quadcopter How to Fly:
- Design a deep reinforcement learning agent to control several quadcopter flying tasks, including take-off, hover, and landing.