Practical Deep Learning for Coders, v3

Text-based and video-based introductory Machine Learning course taught by an experienced instructor and Kaggle's #1 competitor. Using PyTorch and fastai library, this tutorial is focused on practical results rather than theory.

Created by: Jeremy Howard

Produced in 2019

icon
What you will learn

  • Train an image classifier to accurately differentiate cats and dogs
  • Clasify positive and negative movie reviews with revolutionary NLP ULMFiT algorithm
  • Build your own deep learning libraries.
  • Use Camvid dataset for image segmentation
  • Create image classification model and gradient descent loop
  • Important ML techniques of skip connection, U-net architecture, feature loss and gram loss
  • How to implement callbacks and event handlers.
  • Create fastai Data Block API from scratch
  • Implement advanced training techniques such as Mixed precision training, Label smoothing, xresnet
  • Build deep learning library in Swift
  • Much, Much more!

icon
Quality Score

Content Quality
/
Video Quality
/
Qualified Instructor
/
Course Pace
/
Course Depth & Coverage
/

Overall Score : 86 / 100

icon
Live Chat with CourseDuck's Co-Founder for Help

Need help deciding on a machine learning course? Or looking for more detail on Jeremy Howard's Practical Deep Learning for Coders, v3? Feel free to chat below.
Join CourseDuck's Online Learning Discord Community

icon
Course Description

icon
machine learning Awards Best Practical Course

Welcome! If you're new to all this deep learning stuff, then don't worry - we'll take you through it all step by step. (And if you're an old hand, then you may want to check out our advanced course: Deep Learning From The Foundations.) We do however assume that you've been coding for at least a year, and also that (if you haven't used Python before) you'll be putting in the extra time to learn whatever Python you need as you go. (For learning Python, we have a list of python learning resources available.)You might be surprised by what you don't need to become a top deep learning practitioner. You need one year of coding experience, a GPU and appropriate software (see below), and that's it. You don't need much data, you don't need university-level math, and you don't need a giant data center. For more on this, see our article: What you need to do deep learning.The easiest way to get started is to just start watching the first video right now! On the sidebar just click ''Lesson'' and then click on lesson 1, and you'll be on your way.

icon
Pros

icon
Cons

    • Experienced instructor that provides easy to understand explanations and teaches you "how-to" instead of "why".
    • Top-down learning approach perfect for students that want to apply Machine Learning fast.
    • Great community of fellow-learners to help you along the course.
    • This course uses fastai library that can be too difficult for beginners.
    • To understand the theory befind the course, further readings and additional information are necessary.

icon
Instructor Details

Jeremy Howard

Jeremy Howard is an entrepreneur, business strategist, developer, and educator. Jeremy is a founding researcher at fast.ai, a research institute dedicated to making deep learning more accessible. He is also a faculty member at the University of San Francisco, and is Chief Scientist at doc.ai and platform.ai. Jeremy has invested in, mentored, and advised many startups, and contributed to many open source projects.

icon
Reviews

4.3

24 total reviews

5 star 4 star 3 star 2 star 1 star
% Complete
% Complete
% Complete
% Complete
% Complete

By Jason Brownlee on 1/17/2019

The course is excellent.Jeremy is a master practitioner and an excellent communicator.The level of detail is right: high-level first, then lower-level, but all how-to, not why.Application focused rather than technique focused.If youre a deep learning practitioner or you want to be, then the course is required viewing.The videos are too long for me. I used the YouTube playlist and watched videos on double time while I took notes in a text editor.I am not interested in using the fast.ai library or pytorch at this stage, so I skimmed or skipped over the code specific parts. In general, I prefer not to learn code from video, so I would skip these sections anyway.

By Raimi Karim on 5/26/2019

I really love this course. Here are some reasons why:They give intuitions and easy-to-understand explanations.They supplement their courses with great resources.They encourage you to apply deep learning to your respective domains to build things.They seem like theyre always up to date with interesting and novel publications, and incorporate them into the fastai library where appropriate.They also do a lot of research on deep learning (read: ULMFiT).They have built a community around the fastai library hence you will get support easily.Their tips and tricks are good for Kagglers and accuracy-driven modelling.

By URLSweatshirt on 1/30/2019

Course is amazing, library is amazing. I'm learning so much and it works on the real-world problems I'm working on so effortlessly

By Roboserg on 5/27/2018

The theory is great but I didnt like the use of their fastai library. It should be Keras or smth. similar for beginners.

By cedrickchee on 5/8/2018

First of all, I just want to say thanks to Jeremy and Rachel for the courses. I can't say enough good things about the courses. The course may not be for everyone, but it is definitely for me. Granted, each person has their own learning style. Top-down vs. bottom-up approach: some learn better starting from theory, some learn better starting from practical application. I enjoy the approach because I can later dive deeper (reaching into the theory) to understand it better.

By regnus418 on 2/1/2017

After watching the lectures, doing readings and going through notebooks and trying to replicate results myself I now feel confident that I can deploy a deep learning model and achieve good results. Thank you very much for this opportunity!

By ragnarkar on 2/9/2019

This course is best if you want to start building ML models right away rather than spending a lot of time learning the theory

By Spoetnik1 on 5/11/2018

It teaches all the steps in the neural network, tells you all the tricks and covers them quite well. It does require extra reading and additional information to fully get it. Overall it has the feel of a graduate course and I think someone without basic (as in standard curriculum for engineers) statistics, linear algebra and probability theory will struggle and get a lot less out of it.

By Jason Brownlee on 1/17/2019

The course is excellent.Jeremy is a master practitioner and an excellent communicator.The level of detail is right: high-level first, then lower-level, but all how-to, not why.Application focused rather than technique focused.If youre a deep learning practitioner or you want to be, then the course is required viewing.The videos are too long for me. I used the YouTube playlist and watched videos on double time while I took notes in a text editor.I am not interested in using the fast.ai library or pytorch at this stage, so I skimmed or skipped over the code specific parts. In general, I prefer not to learn code from video, so I would skip these sections anyway.

By Raimi Karim on 5/26/2019

I really love this course. Here are some reasons why:They give intuitions and easy-to-understand explanations.They supplement their courses with great resources.They encourage you to apply deep learning to your respective domains to build things.They seem like theyre always up to date with interesting and novel publications, and incorporate them into the fastai library where appropriate.They also do a lot of research on deep learning (read: ULMFiT).They have built a community around the fastai library hence you will get support easily.Their tips and tricks are good for Kagglers and accuracy-driven modelling.

By Roboserg on 5/27/2018

The theory is great but I didnt like the use of their "fastai" library. It should be Keras or smth. similar for beginners.

By ragnarkar on 2/9/2019

This course is best if you want to start building ML models right away rather than spending a lot of time learning the theory