Edit product


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

"This book is very special: in addition to valuable lessons and insights, it contains an outpouring of love for so many people and so many things.

I can't recall anything else that is written with so much humility and love that deals with tech. It's a glorious anti-pattern."

Hamel Husain (@HamelHusain), Staff Machine Learning Engineer at Github, Core Developer at fast.ai

I learned to program and do deep learning using online resources. Most of my income over the last two years has come from deep learning roles. How did I do it? What did I learn along the way?

Maybe you are 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.

I have spent the last couple of years studying how they do it. In this book, I share everything that I learned.

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.

That is what this book is about.

I share the introduction to the book here (temporarily moved to this address while I work on updating my blog -- apologies for the inconvenience!). In it, I outline why I feel qualified to speak to the above.

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.

Need-based financial help

We all come from different walks of life; we live in countries that vary greatly. I strongly believe that everyone should be able to access learning materials as this can change our lives for the better. If you are unable to afford Meta Learning at the listed price, please PM me on Twitter a price that you can comfortably pay.

Refund Policy

If you're not 100% satisfied with the purchase, or if it's not what you were expecting, just reply to the download email within 30 days, and you'll get a full refund. No questions asked.

Praise from others

"If you are starting out in deep learning, this is the book! It distills what I perceived as my own hard-won experience from being on the ML internet since 2012-ish into a pocketable 80 pages. (...)

It's short and concise and an enjoyable read. Found myself reading and nodding: Turns out Radek really captured the essence of all of it. It's a hard recommend!

Sebastian Raschka(@rasbt), Asst Prof of Statistics at the University of Wisconsin-Madison, author of "Python Machine Learning", Machine Learning & Deep Learning researcher

"Inspiring, insightful & reassuring for anyone looking to make a career in Machine Learning 🎉

Thanks @radekosmulski for publishing this wonderful resource! 🙏"

— Rohan Rao(@vopani), Data Scientist H2O.ai, Quadruple Kaggle Grandmaster

"If there's only one source of advice that I could read when starting my ML Journey, it would be the ones in this book"

Sanyam Bhutani (@bhutanisanyam1), Host of Chai Time Data Science, ML Engineer and AI Content Creator at H2O.ai

"This is a slide from @jeremyphoward's talk on "How to fast.ai" - live right now at @QLD_AI_Hub.

Wonderful to see @radekosmulski's "Meta Learning" feature in it! Highly recommend for good practical advice on how to do deep learning & more!"

— Aman Arora(@amaarora), Machine Learning Engineer at Weights & Biases

"If you are looking for a book that will teach you how to learn, I can't think of a better person to learn from than Radek. He is extremely wise and has an amazing perspective on DL and life in general. I'm looking forward to reading his new book!"

Kevin Bird(@kjbird15), Data Scientist at Alliant Energy & Co-Founder of TPSG.io

"I recently made a Twitter thread discussing how to learn and break into data science. I've gotten lots of questions. After reading this book, I think the most helpful answer I can give is to recommend reading it"
— Isaac Flath(@isaac_flath), Applied Machine Learning Researcher at Novettasol

"Just got my own copy, I can't wait to read this. I got a sneak a few months ago and it looked amazing then, excited to read the full thing now!"

— Zach Mueller(@TheZachMueller), Machine Learning Engineer at Novetta

"I devoured the book this evening. Really enjoyable but also lots of prompts to get to work :)"

Alex Strick van Linschoten(@strickvl), Software engineer, researcher (& author of a few books)

"The main reason why Meta learning connects to one's heart is because, while reading Meta learning one doesn't read, Radek's writing, but listens to Radek speaking to you. And that makes all the difference!"

Vignesh Baskaran(@tweetvbaskaran), Data Scientist

"@radekosmulski's book "Meta-Learning" is open, honest and explains how easy it is to develop habits that compound into becoming better at ML while throwing in a ton of useful practices that help you outside of it too! Highly recommend."

— Sairam Sundaresan(@DSaience)

I‘m confident to recommend @radekosmulski's book „Meta Learning“ already after having read only two chapters: „on finding a job“ and „the Deep Learning Party is on Twitter“!

— Lukas Galke(@LukasGalke), PhD student at Christian-Albrechts-Universität zu Kiel

"Have been reading Meta learning by @radekosmulski since two days! I am really blown away by all the sensible tips Radek shares. The book is filled with so many sensible thoughts! Thank you very much Radek! Highly recommended!"

Vignesh Baskaran(@tweetvbaskaran), Data Scientist

"If you're learning ML, especially the @fastdotai way, @radekosmulski's book is a must-have. Short & packed with hard-won insights - can easily save you months of frustration!"

— Tom Walczak(@tom_walchak), Technology Entrepreneur, Founder of @EventIgnite

"Just finished the book. Inspiring, practicable, and actionable. A lot of key lessons for any ML practitioner. Kudos to @radekosmulski for his labor of love. My ML journey has been reignited. Thanks"

Data Hiking(@SeeLifeAsData)

"Got a final version today. Really appreciate all the efforts that was put into the book."

— Ori(@pandarija)

"Enjoyed reading your book. Full of knowledge nuggets for learners like me."

— Alex(@_Alex_Adamov)

"I was waiting for this for a long time. Just got my copy. Enjoying the first few chapters."

— AvinashBeck_(@AvinashBeck14), Building cool products with Machine Learning

"Thank you for writing this. Very practical and touches on useful points for beginners."

— Alex Strick van Linschoten(@strickvl), Software engineer, researcher (& author of a few books)

"Just finished @radekosmulski's book on Meta Learning. It's a great practical resource & not just for new folks. Time to unlearn and relearn! It's got tons of great links, so don't forget to read them and keep making notes."

— Asha Vishwanathan(@ashavish)

"Your book is very logical and insightful. A really good reference to anyone trying to avoid rabbit holes while they are working towards their dreams of either becoming or switching careers into a deep learning practitioner. Thanks a lot for the book."

— saurav_bakshi(@saurav_bakshi)

"(...) it's such an amazing book. especially the answer to the question “Radek, what is the best way to complete the highest amount of mental work over the next 48 hours?”

I can testify that the answer in the book works!"

Owura(@owura_coder), Self-Taught Software Developer

"Your book landed in very first class video of fast.ai 2021 :) more so the reason for me to read this book :)"

— Sandeep Singh(@sandeepsign) Owning Computer Vision @beansmaps @AiLabs, Engineering/Development/Research/Leadership, fast.ai Deep Learning Fellow

"Bought the book half an hour back and already half way through. Sadly, my approach to learning has been very similar to yours initial approach until recently, I have been trying to change it to more practice. It’s a very timely book for me! Thanks"

— Pawan Kumar Singh(@pawansinghds), Data Scientist

"Missed pre-order, but decided to get a copy because of the good introduction. Look forward to reading it!"

— Edwin Hung(@byEdwinHung)

"Have just started reading.

Ch: The Secret of a Good Developer, makes a point that has always been there in the mind and you have actually brought it out loud in words.

Started fast.ai journey sometime back. Looking forward to implementing Meta Learning :) with time."
— Srishti(@srishtigp)

"I am one of the many happy Meta Learning readers. Thanks!"

— David Dirring(@DavidDirring), Principal Data Scientist Home Depot 

21 ratings

  • a 90 page ebook
  • formatmobi, epub, PDF


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

Enter your info to complete your purchase


···· ···· ···· 4242
Test card



Use a different card?


pp paypal

or pay with

We do not keep any of your sensitive credit card information on file with us unless you ask us to after this purchase is complete.

or pay with

You'll be charged US$25.

Your purchase was successful!

We charged your card and sent you a receipt


    Dear Reader,

    Thank you very much for your purchase!

    The trust you are showing me by your interest in my book means a lot to me.

    I hope you enjoy Meta Learning! Would love to hear your feedback :) Should you find anything to not be to your satisfaction, please be aware of the 30-day no-questions-asked refund policy.

    Wishing you all the best in your journey and thank you for inviting me to tag along,

    Good news! Since you already have a Gumroad account, it's also been added to your library.

    Powered by Gumroad