Meta Learning: How To Learn Deep Learning And Thrive In The Digital World

45 ratings

Meta Learning is an actionable roadmap to learning machine learning efficiently. It will show you exactly what you need to learn and how to learn it in order to become a world-class machine learning professional in the least amount of time.

I wrote Meta Learning because on my deep learning journey I discovered a lot of ideas and techniques that can be helpful to others.

Initially, I struggled a lot with learning machine learning. I completed MOOC after MOOC and watched countless lectures on YouTube.

I did learn a lot in the academic sense of the word.

However, when confronted with a real-life machine learning problem I had no clue how to even get started.

This would go on for years.

I started to lose hope that I would amount to anything in machine learning and so I decided to quit. I managed to stay clear of machine learning for 5 months straight.

But my love for it wouldn't wane and I decided to give it one last try. I couldn't trust my approach so out of desperation I decided to try something new.

I would go out of my way and study how the most successful people behaved.

You may be on Twitter. Or maybe you are part of the fast.ai community or participate in Kaggle competitions.

You may have noticed that some individuals seem to learn very fast, hacking on project after project.

These are the people I wanted to learn from and emulate.

And the results were astonishing.

Very soon I won a Kaggle competition.

I have since held several very good, fully remote deep learning roles.

All this as someone without a college degree who started to learn to program at the age of 29.

How did I do it? What did I learn along the way that could be of great help to you?

This is what Meta Learning is all about.

The promise of Meta Learning

This book is a map that will help you navigate learning machine learning. It can speed up your progress several-fold.

Think about the next three years of your life. How differently would they unfold if you could move 5% or 20% quicker? What if you 3x or 4x the speed at which you learn?

No superhuman effort is required. In fact, in many cases, overexerting yourself is counterproductive to your long-term progress.

However, the way we go about things—the mental models we operate under—can make a world of difference.

These empowering ways of looking at the world around you and effective techniques for learning are precisely what this book will give you.

From this book, among other things, you'll learn:

how to learn machine learning efficiently
the proven strategies to improve as a developer
how to approach the tools you use for work and why it matters
how to reason about the hardware you use for best results and to make sure you invest your time where it's worthwhile
what makes sharing your work so powerful
one way to reason about finding a mentor
how to keep in touch with the deep learning community and stay up to date with trends in research for the least amount of work
an effective way to become employable without a formal background (tailored to the digital age we live in now)
how to build a habit and why the path of little resistance is the way to go
one way to find the energy to do deep learning

All of the above is based on my experience. I cover the ideas and strategies that worked best for me, out of many that I tried.

You can find the introductory chapter on my blog here. In it, I outline why I feel qualified to speak to the above.