A few resources to get into Deep Learning

Before making some recommendations I’d like to mention that I don’t have the absolute truth, this is simply a path that resonates with me because my personality is geared towards more practical resources. I usually like to delve into theory after I know the basics.

Now that I made that clear, these are some resources I’d recommend to the young me if I were to start learning this from zero:

• Deep Learning with Python: written by the great Francois Chollet, creator of the Deep Learning framework called Keras. It’s in my opinion an almost perfect book for someone who’s just starting, it contains chapters with the right balance between theory and practice with great code examples. Python is the programming language used in the book and Keras the framework, I don’t think it’d be a problem if you don’t know them beforehand.
• Deep learning for coders: what a great course! It’s open, free, has a top-down approach, starting with a working projects and then slowly delving into each piece of code. It’s more complete than the mentioned book but a little more disorganized if you want to learn something specific. For example, if you want to know how a CNN works, you’ll have to watch several lessons ir order to see the whole picture. So maybe if you don’t do the whole course there’ll be some concepts you won’t fully grasp. A nice approach would be to consume this course and the book in parallel.

If you conciously read and watch those two resources you’ll have a nice grasp of the theory and practice and you’ll be able to apply the knowledge to your own projects or start working for someone else. You won’t be an expert after it, give it a little time and experience :P.

After that, there are several options depending on your own needs:

• Start working in your own projects, learn as needed.
• Go through domain specific Deep Learning courses. If you’re interested in Medical AI, this is an interesting one.
• Compete with other people on Kaggle.
• Go deep in theory, maybe with this great book, Stanford has great detailed courses also.

That’s it, simple and short. Of course that there’s a gazillion of courses, tutorials, projects, open repositories, workshops and other materials in the web, my advice is to just pick something and have the determination to follow through. It’s really easy to drown in a sea of resources nowadays, simplicity is the best way to avoid it.