Nanodegree Program

Deep Learning

Build Deep Learning Models Today

Deep learning is driving advances in artificial intelligence that are changing our world. Enroll now to build and apply your own deep neural networks to challenges like image classification and generation, time-series prediction, and model deployment.

Enrollment Closing In

  • Time
    1 Four-Month Term

    Study 12 hrs/week and complete in 4 mo.

  • Classroom Opens
    April 30, 2019

    Classroom opens 7 days after enrollment closes

In Collaboration With
  • Amazon Web Services
  • Facebook Artificial Intelligence

Why Take This Program?

In this program, you’ll cover Convolutional and Recurrent Neural Networks, Generative Adversarial Networks, Deployment, and more. You’ll use PyTorch, and have access to GPUs to train models faster. You'll learn from authorities like Sebastian Thrun, Ian Goodfellow, Jun-Yan Zhu, and Andrew Trask. This is the ideal point-of-entry into the field of AI.

Why Take This Program?

The share of jobs requiring AI skills has grown 4.5x since 2013

Expert Instructors
Expert Instructors

Expert Instructors

Learn practical skills taught by deep learning experts including Sebastian Thrun, Ian Goodfellow, Jun-Yan-Zhu, Andrew Trask, and the Udacity Deep Learning Team.

Unique Projects, Personalized Feedback

Unique Projects, Personalized Feedback

Work on five specially-designed deep learning projects, and receive detailed feedback on each from our mentors.

Deploy Your Own Sentiment Analysis Model
Deploy Your Own Sentiment Analysis Model

Deploy Your Own Sentiment Analysis Model

You’ll get hands-on experience deploying and monitoring a model using PyTorch and Amazon SageMaker. By teaching these essential skills, we are preparing our students to be indispensable members of AI product teams.

Guaranteed Admission

Guaranteed Admission

Successfully complete the program, and receive guaranteed admission to either our Self-Driving Car Engineer or Flying Car Nanodegree programs.

Guaranteed Admission

As a graduate, you earn guaranteed admission into one of two other Nanodegree program. You’ll continue to explore even more deep learning projects alongside groundbreaking new curriculum built with our pioneering industry collaborators. Note that we recommend some C++ knowledge to get the most out of these programs.

Step 1

Enroll in the Deep Learning Nanodegree program

Step 2

Graduate within 4 months

Step 3

Enroll in one of two advanced Nanodegree programs with guaranteed admission

What You Will Learn

Download Syllabus

Deep Learning

Become an expert in neural networks, and learn to implement them using the deep learning framework PyTorch. Build convolutional networks for image recognition, recurrent networks for sequence generation, generative adversarial networks for image generation, and learn how to deploy models accessible from a website.

Master building and implementing neural networks for image recognition, sequence generation, image generation, and more.

See fewer details

4 months to complete

Prerequisite Knowledge

This program has been created specifically for students who are interested in machine learning, AI, and/or deep learning, and who have a working knowledge of Python programming, including NumPy and pandas. Outside of that Python expectation and some familiarity with calculus and linear algebra, it's a beginner-friendly program.See detailed requirements.

  • Introduction

    Get your first taste of deep learning by applying style transfer to your own images, and gain experience using development tools such as Anaconda and Jupyter notebooks.

  • Neural Networks

    Learn neural networks 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.

    Predicting Bike-Sharing Patterns
  • 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.

    Dog-Breed Classifier
  • 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.

    Generate TV scripts
  • 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.

    Generate Faces
  • Deploying a Sentiment Analysis Model

    Train and deploy your own PyTorch sentiment analysis model. 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.

    Deploying a Sentiment Analysis Model
Just as machines made human muscles a thousand times stronger, machines will make the human brain a thousand times more powerful.

In Collaboration with Top Industry Experts

Sebastian Thrun
Sebastian Thrun
Founder, Google X, Self-Driving Car Pioneer
Ian Goodfellow
Ian Goodfellow
Inventor of GANs, Author of Deep Learning (MIT Press)
Jun-Yan Zhu
Jun-Yan Zhu
Researcher at MIT CSAIL and coauthor of CycleGAN
Andrew Trask
Andrew Trask
Author of Grokking Deep Learning, Google DeepMind Scholar

Learn with the best

Mat Leonard
Mat Leonard

Product Lead

Mat is a former physicist, research neuroscientist, and data scientist. He did his PhD and Postdoctoral Fellowship at the University of California, Berkeley.

Luis Serrano
Luis Serrano

Head of Content

Luis was formerly a Machine Learning Engineer at Google. He holds a PhD in mathematics from the University of Michigan, and a Postdoctoral Fellowship at the University of Quebec at Montreal.

Cezanne Camacho
Cezanne Camacho

Curriculum Lead

Cezanne is a computer vision expert with a Masters in Electrical Engineering from Stanford University. As a former genomics and biomedical imaging researcher, she’s applied computer vision and deep learning to medical diagnostics.

Alexis Cook
Alexis Cook


Alexis is an applied mathematician with a Masters in computer science from Brown University and a Masters in applied mathematics from the University of Michigan. She was formerly a National Science Foundation Graduate Research Fellow.

Jennifer Staab
Jennifer Staab


Jennifer has a PhD in Computer Science, Masters in Biostatistics, and was a professor at Florida Polytechnic University. She previously worked at RTI International and United Therapeutics as a statistician and computer scientist.

Sean Carrell
Sean Carrell


Sean Carrell is a former research mathematician specializing in Algebraic Combinatorics. He completed his PhD and Postdoctoral Fellowship at the University of Waterloo, Canada.

Ortal Arel
Ortal Arel


Ortal Arel is a former computer engineering professor. She holds a Ph.D. in Computer Engineering from the University of Tennessee. Her doctoral research work was in the area of applied cryptography.

Jay Alammar
Jay Alammar


Jay is a software engineer, the founder of Qaym (an Arabic-language review site), and the Investment Principal at STV, a $500 million venture capital fund focused on high-technology startups.

Student Reviews



5 stars
4 stars
3 stars
2 stars
1 stars
Eigenvalue l.

Very useful content and interesting projects

Andrew B.

Excellent content and projects!

Farhan Z.

yes it is quite comprehensive in every way. Especially liked the extra material on Attention based models and a comprehensive view of GANs. The material on LSTM internal structure was excellent and the best description of LSTM gating structure I could find anywhere. Great Job!!!

Swaminathan S.

It is a great foundation for Deep learning Models and its architecture. Each section in course are designed with well thought process, completing each section properly will give great clarity to do the respective projects at each section.

Greg B.

This program was great. Covered all the basics and some more sophisticated models.

Nanodegree program
Deep Learning
$999 USD


Learn to build the deep learning models that are revolutionizing artificial intelligence.

Program Details

  • Why should I enroll?

    In this program, you’ll master deep learning fundamentals that will prepare you to launch or advance a career, and additionally pursue further advanced studies in the field of artificial intelligence. You will study cutting-edge topics such as neural, convolutional, recurrent neural, and generative adversarial networks, as well as sentiment analysis model deployment. You will build projects in Keras and NumPy, in addition to TensorFlow PyTorch. You will learn from experts in the field, and gain exclusive insights from working professionals. For anyone interested in building expertise with this transformational technology, this Nanodegree program is an ideal point-of-entry.

  • What jobs will this program prepare me for?

    This program is designed to build on your skills in deep learning. As such, it doesn't prepare you for a specific job, but expands your skills in the deep learning domain. These skills can be applied to various applications and also qualify you to pursue further studies in the field.

  • How do I know if this program is right for me?

    If you are interested in the fields of artificial intelligence and machine learning, this Nanodegree program is the perfect way to get started!

  • Do I need to apply? What are the admission criteria?

    No. This Nanodegree program accepts all applicants regardless of experience and specific background.

  • What are the prerequisites for enrollment?

    Students who are interested in enrolling must have intermediate-level Python programming knowledge, and experience with NumPy and pandas. You will need to be able to communicate fluently and professionally in written and spoken English. Additionally, students must have the necessary math knowledge, including: algebra and some calculus—specifically partial derivatives, and matrix multiplication (linear algebra).

  • If I do not meet the requirements to enroll, what should I do?
  • How is this Nanodegree program structured?

    The Deep Learning Nanodegree program is comprised of one (1) Term of four (4) months. A Term has fixed start and end dates.

    To graduate, students must successfully complete five (5) projects, each of which affords you the opportunity to apply and demonstrate new skills that you learn in the lessons. Each project will be reviewed by the Udacity reviewer network. Feedback will be provided and if you do not pass the project, you will be asked to resubmit the project until it passes.

  • How long is this Nanodegree program?

    Access to this Nanodegree program runs for the period noted in the Term length section above.

    See the Terms of Services and FAQs for other policies around the terms of access to our Nanodegree programs.

  • Can I switch my start date? Can I get a refund?

    Please see the Udacity Nanodegree program FAQs found here for policies on enrollment in our programs.

  • I have graduated from the Deep Learning Nanodegree program but I want to keep learning. Where should I go from here?

    Graduates from this Nanodegree program earn guaranteed admitted status into our more advanced Self-Driving Car Engineer or Flying Car Nanodegree programs, subject to payment by student for the cost of enrollment for those Nanodegree programs.

  • What is “Guaranteed Admission”?

    Some Nanodegree programs, due to the complexity of the material, require prerequisites and/or an application process to ensure that students who enroll are qualified to meet the demands of the course. However, in those instances where students have graduated from other Udacity courses that we feel adequately prepare them for our more advanced courses, we will guarantee that they will be allowed to enroll subject to paying the Nanodegree program fees.

  • What software and versions will I need in this program?

    Virtually any 64-bit operating with at least 8GB of RAM will be suitable. Students should also have Python 3 and Jupyter Notebooks installed. For the more intensive portions of the program that come later, we will be providing students with AWS instances where geographically possible.

Deep Learning

Build Deep Learning Models Today