This article was originally adapted from a podcast, which you can check out here.
Sometimes, during guest interviews, I mention the existence of my deep learning book or my mathematical foundations of machine learning course.
It recently occurred to me, however, that I’ve never taken a step back to detail exactly what content I’ve published over the years and where it’s available if you’re interested in it. So, today I’m dedicating a Five-Minute Friday specifically to detailing what all of my deep learning content is and where you can get it. In next week’s episode, I’ll dig into my math for machine learning content. But, yes, for today, it’s all about deep learning.
Whether you’re interested in learning about deep learning from scratch or you’re interested in specializing in some specific application of deep learning (such as natural language processing, machine vision, or deep reinforcement learning), much of my deep learning content can be accessed for free via YouTube. I’ve gathered the videos in the “Talks and Tutorials” playlist of my YouTube channel and we’ve included a link to this playlist in the show notes. This playlist includes:
A two-hour hands-on tutorial on how deep learning works
A two-hour introduction to natural language processing with deep learning
A two-hour introduction to using convolutional neural networks for machine vision, and
An hour-long hands-on introduction to a deep reinforcement approach called Deep Q Learning that has — incredibly — been viewed over 60,000 times.
All in all, that’s quite a lot of free deep learning tutorials: eight hours in total, which is nearly half of the 17 hours of video tutorials on deep learning I’ve created overall. To access the remainder, the most cost-effective way is via the O’Reilly learning platform. At many companies around the world, access to the O’Reilly learning platform is provided by your employer so you could ask around to see if you already have access to a subscription.
That said, if you don’t already have an O’Reilly subscription personally or through your employer, they offer a ten-day free trial, which is more than enough time to watch my deep learning videos. I’m also working with O’Reilly now to obtain a 30-day free trial for SuperDataScience listeners so stay tuned for the details of that announcement hopefully in the near future.
In any event, my deep learning curriculum in the O’Reilly platform is split up over three separate video tutorial series:
The first is called Deep Learning with TensorFlow, Keras, and PyTorch; this is a seven-hour hands-on introduction to deep learning in general and is where you should start if you’re new to deep learning
The second is called Deep Learning for Natural Language Processing and, over the course of five hours, introduces how to design models to make predictions with natural language data.
The third and final video series is called Machine Vision, Generative Adversarial Networks, and Deep Reinforcement Learning; over six hours, this covers these categories of relatively advanced deep learning applications.
Oh, and I should mention that all of the code for these videos is freely available open-source in GitHub — we’ve provided a link to my deep learning GitHub repo in the show notes as well.
Having mentioned all that, if you’d like to access my entire deep learning curriculum — all of the content covered in the video tutorials as well as all of the associated code, wrapped up neatly in one single place — you can get that from my book, Deep Learning Illustrated. Like the videos, it’s available digitally within the O’Reilly learning platform, but you can also order digital or physical copies of it from booksellers all over the world. I’ve included a link in the show notes from which you can purchase it at a 35% discount. For our international listeners, that link also includes details of where you can find translations of Deep Learning Illustrated, including German, Korean, Russian, Polish, and Traditional Chinese versions. In addition to those, Japanese and Simplified Chinese versions are in the works.
All right, so that was a summary of the various methods of undertaking my deep learning curriculum. While teaching this deep learning content to students online and in-person, I discovered that many folks could use a primer on the foundational subjects that underlie machine learning in general and deep learning in particular. So after publishing all my deep learning content, I set to work on creating content that covers these foundational subjects — namely linear algebra, calculus, probability, statistics, and computer science. For Five-Minute Friday next week, I’ll fill you in on where this growing body of content is available, including where I’m publishing 100% free versions of all of it.
Until then, keep on rockin’ it out there. I’m looking forward to catching you on another round of SuperDataScience very soon.