A Udacity course on deep learning, originally developed with Google, covering neural networks and their practical implementation with TensorFlow. It is the capstone of Udacity's data science and machine learning sequence in the comments.

Commenters recommend it as a hands-on deep learning course, with one calling it the Google deep learning class and another highly recommending it for beginners.

What commenters said (7)

1. Strongly recommendspartycoder2016in “MNIST Handwritten Digit Classifier – beginner neural network project”

   If you want to jump into this sort of thing, I highly recommend Google's Udacity course for deep learning. https://classroom.udacity.com/courses/ud730

2. Recommendslerax2017in “Ask HN: Best way to get started with AI?”

   Nice to some one pointing the fundamentals. A good understanding about probabilist models is good too. After getting into too the basic math knowledge, I suggest this: https://classroom.udacity.com/courses/ud730

3. Recommendsccmonnett2016in “TensorFlow Simplified Interface Examples”

   Hey, I signed up just to reply! If you want to begin to understand the stuff for fun I recommend the Udacity cluster of data science courses - intro to data science, machine learning, and eventually deep neural networks. I took AI at Stanford and learned a TON but for getting your hands dirty fast the Udacity courses are more appropriate. They have a bunch and they are well segmented so if you want to divert into e.g. data visualization, there's a class for that.

   Your learning will culminate in this course: https://www.udacity.com/course/deep-learning--ud730

4. Recommendsrichieb2016in “Ask HN: Deep learning tutorials for hands-on learners?”

   Check out this course: https://www.udacity.com/course/deep-learning--ud730

5. Mentionsolivercameron2018in “Self-Driving Car Startup Voyage Brings on Ex-Tesla, Cruise and Uber Exec as CTO”

   Hello! Great questions.

   1) If you already have a good grasp of Python, I always advise to start with the AI for Robotics MOOC at Udacity, which is my favorite class of all time. Once that's done, I'd take a look at their Deep Learning classes and the Self-Driving Car Nanodegree.

   2) I think it's crucial to get to grips with how the whole stack works, so I always advise to get to grips with a middleware like ROS. Also, don't be afraid to dabble in algorithms (think problems in motion planning, computer vision, etc.)

   3) The traditional programs (think PhD programs) create a lot of specialists focused on a single domain, but the industry is in dire need of more generalists. An engineer who is able to dive into any part of the stack is a huge value-add!

6. Mentions2_listerine_pls2017in “Deeplearning.ai: Announcing New Deep Learning Courses on Coursera”

   No, it's not a matter of learning styles. Rather, it's a matter of preference. I prefer rigorous coverage and quality.

   Just take a look at Udacity's deep learning reviews @ class-central.com

7. Mentionsmindcrime2016in “Ask HN: What do you want to learn in 2016?”

   I also just finished the Coursera ML course, now I'm doing some stats and data science classes on there, and the Google deep learning class at Udacity.

   I kinda think that the rise of MOOCs and "on demand education" is the best thing since sliced bread. :-)

Related courses

• Machine Learning (Andrew Ng)Coursera · 240 recommenders
• Artificial Intelligence for RoboticsUdacity · 10 recommenders
• Self-Driving Car Engineer NanodegreeUdacity · 11 recommenders
• Machine LearningUdacity · 4 recommenders
• Intro to Data ScienceUdacity · 1 recommender
• Practical Deep Learning for Codersfast.ai · 112 recommenders
• CS231n: Convolutional Neural Networks for Visual RecognitionStanford University · 39 recommenders
• Deep Learning Specialization (Andrew Ng)Coursera · 31 recommenders