Deep Learning Nanodegree  

This repository contains some my work from the Deep Learning with pytorch Udacity NanoDegree.

Course 1

Introduction to Deep Learning

Introduce yourself to deep learning by applying style transfer to your own images, and gaining experience using development tools such as Anaconda and Jupyter notebooks.

Course Project: Build a Neural Network  

Build and train your own Neural Network.

Course 2

Neural Networks

Learn neural network basics, and build your first network with Python and NumPy. Use the modern deep learning framework PyTorch to build multi-layer neural networks, and analyze real data

Lessons:

Neural Networks, Implementing Gradient Descent, Training Neural Networks, Sentiment Analysis

Course Project: Predicting Bike-Sharing Patterns  

Build and train your own Neural Network from scratch to predict the number of bikeshare users on a given day.

Course 3

Convolutional Neural Networks

Learn how to build convolutional networks and use them to classify images (faces, melanomas, etc.) based on patterns and objects that appear in them. Use these networks to learn data compression and image denoising.

Lessons:

CNNs, Cloud Computing, Transfer Learning, Weight Initialisation, Autoencoders, Style Transfer

Course Project: Dog-Breed Classifier  

In this project, you will learn how to build a pipeline to process real-world, user-supplied images. Given an image of a dog, your algorithm will identify an estimate of the canine’s breed

Course 4

Recurrent Neural Networks

Build your own recurrent networks and long short-term memory networks with PyTorch; perform sentiment analysis and use recurrent networks to generate new text from TV scripts.

Lessons:

Recurrent Neural Networks, LSTMs, Implementation of RNN & LSTM, Hyperparameters, Embeddings & Word2Vec, Sentiment Prediction RNN

Course Project: Generate TV Scripts  

Generate a TV script by defining and training a recurrent neural network

Course 5

Generative Adversarial Networks

Learn to understand and implement a Deep Convolutional GAN (generative adversarial network) to generate realistic images, with Ian Goodfellow, the inventor of GANs, and Jun-Yan Zhu, the creator of CycleGANs

Lessons:

GANs, Deep Convolutional GANs, Pix2Pix & CycleGANS, Implementing a CycleGAN

Course Project: Generate Faces  

Define two adversarial networks, a generator and discriminator, and train them until you can generate realistic faces.

Course 6

Deploying a Model

Train and deploy your own sentiment analysis model using Amazon's SageMaker. Deployment gives you the ability to use a trained model to analyze new, user input. Build a model, deploy it, and create a gateway for accessing it from a website.

Lessons:

Deployment, Sagemaker Model Deployment, Hyperparameter Tuning, Updating a Model

Course Project: Deploying a Sentiment Analysis Model  

In this project, you will build and deploy a neural network which predicts the sentiment of a user-provided movie review. In addition, you will create a simple web app that uses your deployed model.