Deep Learning

Welcome to the Deep Learning Nanodegree program! Learn about the program structure and resources!

The Careers team at Udacity is here to help you move forward in your career - whether it's finding a new job, exploring a new career path, or applying new skills to your current job.

You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.

What to do if you have questions about your account or general questions about the program.

Anaconda is a package and environment manager built specifically for data. Learn how to use Anaconda to improve your data analysis workflow.

In this lesson, you'll experiment with a few examples of deep learning. This is meant to get you acquainted with a variety of applications, then later you'll learn the details of how they work!

Learn how to use Jupyter Notebooks to create documents combining code, text, images, and more.

In this lesson, you'll review the matrix math you'll need to understand to build your neural networks. You'll also explore NumPy, the library you'll use to efficiently deal with matrices in Python.

In this lesson, Luis will teach you the foundations of deep learning and neural networks. You'll also implement gradient descent and backpropagation in python, right here in the classroom!

Mat will introduce you to a different error function and guide you through implementing gradient descent using NumPy matrix multiplication.

Now that you know what neural networks are, in this lesson you will learn several techniques to improve their training.

See a demonstration of GPU workspaces in the Udacity classroom.

In this lesson, Andrew Trask, the author of Grokking Deep Learning, will walk you through using neural networks for sentiment analysis.

In this project, you'll build and train your own Neural Network from scratch to predict the number of bikeshare users on a given day. Good luck!

Project Description - Predicting Bike-Sharing Patterns

Project Rubric - Predicting Bike-Sharing Patterns

Learn how to use PyTorch for building deep learning models

Convolutional Neural Networks allow for spatial pattern recognition. Alexis and Cezanne go over how they help us dramatically improve performance in image classification.

See a demonstration of GPU workspaces in the Udacity classroom.

Take advantage of Amazon's GPUs to train your neural network faster. In this lesson, you'll setup an instance on AWS and train a neural network on a GPU.

Learn how to apply a pre-trained network to a new problem with transfer learning.

In this lesson, you'll learn how to find good initial weights for a neural network. Having good initial weights can place the neural network closer to the optimal solution.

Autoencoders are neural networks used for data compression, image de-noising, and dimensionality reduction. Here, you'll build autoencoders using PyTorch.

Learn how to use a pre-trained network to extract content and style features from an image. Implement style transfer with your own images!

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.

Project Description - Dog-Breed Classifier

Project Rubric - Dog-Breed Classifier

In this lesson, Sebastian Thrun teaches us about his groundbreaking work detecting skin cancer with convolutional neural networks.

To kick off your industry research, learn about real world applications of Deep Learning and common questions about jobs in this field.

Other professionals are collaborating on GitHub and growing their network. Submit your profile to ensure your profile is on par with leaders in your field.

Project Description - Optimize Your GitHub Profile

Project Rubric - Optimize Your GitHub Profile

Explore how memory can be incorporated into a deep learning model using recurrent neural networks (RNNs). Learn how RNNs can learn from and generate ordered sequences of data.

Luis explains Long Short-Term Memory Networks (LSTM), and similar architectures which have the benefits of preserving long term memory.

Learn how to represent memory in code. Then define and train RNNs in PyTorch and apply them to tasks that involve sequential data.

Learn about a number of different hyperparameters that are used in defining and training deep learning models. We'll discuss starting values and intuitions for tuning each hyperparameter.

In this lesson, you'll learn about embeddings in neural networks by implementing the Word2Vec model.

Implement a sentiment prediction RNN for predicting whether a movie review is positive or negative!

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

Project Description - Generate TV Scripts

Project Rubric - Generate TV Scripts

Attention is one of the most important recent innovations in deep learning. In this section, you'll learn how attention models work and go over a basic code implementation.

Ian Goodfellow, the inventor of GANs, introduces you to these exciting models. You'll also implement your own GAN on the MNIST dataset.

In this lesson you'll implement a Deep Convolution GAN to generate complex color images of house numbers.

Jun-Yan Zhu, on of the creators of the CycleGAN, will lead you through Pix2Pix and CycleGAN formulations that learn to do image-to-image translation tasks!

Cezanne will show you how to implement a CycleGAN in PyTorch and translate images from the summer to winter domains.

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

Project Description - Generate Faces

Project Rubric - Generate Faces

Find your next job or connect with industry peers on LinkedIn. Ensure your profile attracts relevant leads that will grow your professional network.

Project Description - Improve Your LinkedIn Profile

Project Rubric - Improve Your LinkedIn Profile

This lesson will familiarizing the student with cloud and deployment terminology along with demonstrating how deployment fits within the machine learning workflow.

Learn how to use Amazon’s SageMaker service to predict Boston housing prices using SageMaker’s built-in XGBoost algorithm.

In this lesson students will learn how to deploy a model using SageMaker and how to make use of their deployed model with a simple web application.

In this lesson students will see how to use SageMaker’s automatic hyperparameter tuning tools on the Boston housing prices model from lesson 2 and with a sentiment analysis model.

In this lesson students will learn how to update their model to account for changes in the underlying data used to train their 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.

Project Description - Deploying a Sentiment Analysis Model

Project Rubric - Deploying a Sentiment Analysis Model

In this section, you will learn some of the most common metrics used to evaluate deep learning models.

Luis gives you a foundation on linear regression, and some non-linear extensions, including the use of neural networks.

In this lesson, you'll build your own small version of TensorFlow, called MiniFlow. By building this, you'll gain an understanding of how TensorFlow works under the hood, and gain more insights into important concepts like backpropagation.

In this section you'll define a neural network with Keras, and apply the framework to analyze movie reviews.

Learn to define and train convolutional neural networks in Keras, as well as implement data augmentation and transfer learning.

In this section you'll get an introduction to TensorFlow, Google's deep learning framework, and you'll be able to apply it on an image dataset.