Nanodegree Program

Deep Learning

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 produce amazing solutions to important challenges.


  • Time
    1 Four-Month Term

    Study 12 hrs/week and complete in 4 mo.

  • Classroom Opens
    January 15, 2019
  • Prerequisites
    Python, Machine Learning, Maths

    See prerequisites in detail

  • Language

    Learning material and communication in English

Why Take This Nanodegree 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 Nanodegree Program?

AI-driven global software revenue will top $30B in 2020

Expert Instructors
Expert Instructors

Expert Instructors

Learn practical skills taught by deep learning experts including Sebastian Thrun, Ian Goodfellow, 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 our Self-Driving Car Engineer, Artificial Intelligence, or Flying Cars and Autonomous Flight Nanodegree programs, subject to your payment of costs of enrollment!

Office Hours with our Experts-in-Residence

Benefit from the opportunity to connect directly with our Udacity Experts-in-Residence, an elite group of data science practitioners working at some of the most data-driven organizations in the world, including Google, Airbnb, IBM Watson, and more. In moderated office hour sessions, you’ll get actionable insights and guidance that will power your progress through our data science courses, and help prepare you for the next steps in your data science future.Connect with our Udacity Experts-in-Residence, working at the most data-driven organizations in the world. You'll get insights and guidance that will power your progress, and prepare you for the next steps in your data science future.

Tom Brown

Google Brain

Anirudh Goyal

Bengio Lab

Adhiguna Kuncor


Jules Pondard

Bengio Lab

Sandeep Subramania

Bengio Lab

Nan Rosemary Ke

Bengio Lab

Guaranteed Admission

As a graduate, you earn guaranteed admission, subject to your payment of program enrollment costs, into one of two advanced Nanodegree programs. 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, and pay for, 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 very 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 modern deep learning frameworks (Keras, TensorFlow) 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 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 Keras and TensorFlow; perform sentiment analysis and generate new text. Use recurrent networks to generate new text from TV scripts.

    Generate TV scripts
  • Generative Adversarial Networks

    Learn to understand and implement the DCGAN model to simulate realistic images, with Ian Goodfellow, the inventor of GANS (generative adversarial networks).

    Generate Faces
  • Deep Reinforcement Learning

    Use deep neural networks to design agents that can learn to take actions in a simulated environment. Apply reinforcement learning to complex control tasks like video games and robotics.

    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)
Andrew Trask
Andrew Trask
Author of Grokking Deep Learning, Google DeepMind Scholar
Jun-Yan Zhu
Jun-Yan Zhu

Learn with the best

Mat Leonard
Mat Leonard

Program 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


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.

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.

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.

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.

Jay Alammar
Jay Alammar


Jay is a software engineer, the founder of Qaym (an Arabic-language review site), and the Investment Principal at the Riyad Taqnia Fund, a $120 million venture capital fund focused on high-technology startups.

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.


Learn now, pay later

To make it even easier to learn, you can finance your Nanodegree through Affirm.

  • Calendar

    Easy monthly payments

    As low as US$84 per month at 0% APR.

    Learn more.

  • Finance

    Flexible Payments

    Pay your monthly bill using a bank transfer, check, or debit card.

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