Make Your Own Neural Network

Who is Tariq Rashid? As I read more and more of this book, finding the answer to this question became paramount. I've read a lot of books, both fiction and non-fiction. In fact, I typically read a book a week. But never have I read a text which as so clear, and concise. Such a perfect marriage of simplicity and information about the subject. I actually didn't want to put the book down! Which is why I had to know about Mr. Rashid. It became clear to me that this man must be among the greatest teachers EVER!What would you normally expect when you buy a book like this? Lots of math? Plenty of dry paragraphs? Definitions on every page? Theorems and proofs? Well, if you do that in this case, you will be disappointed. Instead, what you find is that you will get exactly what you need to understand the topic, and put it into practice. No more, and no less.Mr. Rashid is an absolute master of communicating just what the reader needs to reach the point of understanding. And to get there, he uses a very simple, step-by-step approach. One that builds directly on what has gone before. No hiding the ball. No leaps in logic. Just a simple explanation that leaves no room for doubt (he works through simple examples to hammer needed points home). And at the end of the journey - and indeed, at many points along the way - where are you? I'll tell you where: you will be saying to yourself "I understand this! I got it! I am so happy I bought this book!"I got an inkling of what was to come when I read the appendices (e.g., about the basics of calculus). I figured the appendices in a book often tell you something about the author - what they decided to include, but not as part of the main text. When I finished them, I wondered why I never had a textbook, or even a teacher, like that? Why couldn't everyone explain things in this manner? I know when I give a lecture I try to make things interesting and easy to understand, but I suspect I've never reached this level, since I've never seen anything like it myself. And I've had almost 20 years in school!In the end, I have no doubt that I can use what I've learned. Indeed, I've got some nifty ideas about some ways to try this out, and am looking forward to doing so. So if you're thinking that the subject might be too difficult for you, I'm here to tell you that if you've got high school math, and even if you don't have a programming background, you can still do this!The bottom line is that if you want to learn about the basics of neural networks, THIS IS THE BOOK TO BUY! Don't even think about anything else. GET THIS BOOK!Oh yes, so who is Mr. Rashid? He's a man that is inspired to explain things to others. To really teach them, so that they can work to carry knowledge forward. But he is also a man that is too modest to publish anything about himself in his own books. You can read a little bit about him on amazon.com. That's what I did. He is truly an inspiration to me. Both in building my confidence in my own ability to learn this subject, and in restoring my confidence in others - proving to me that there are still plenty of people that truly want to do something good in this world.And Mr. Rashid, if you read this, I want you to know that you have not failed. No, you have definitely succeeded, in so many ways. Thank you for taking the time to do such great work with this book. I have never seen anything like it, and I hope you will be inspired to continue in your mission. Technical literature is not my favorite genre, not by a long shot, but in your case, I would be proud to stand first in line to buy whatever you care to write. It's that good!

Are you intrigued at how people learn? Want to learn a bit about how the human brain has neurons that are connected to other neurons and in the process of sending signals between them computation and learning takes place?Do you enjoy a bit of mathematics?Do you appreciate authors who are able to take a complex subject and make it really easy to understand?Have you ever dreamed about writing a program that can learn?Have you ever wanted to write programs that weren’t just hacked together; rather, they were built upon solid mathematical principles?Personally, I answer “yes” to all the above. (Although I am really rusty in mathematics).This book, if read, accomplishes all the above. The book is on neural networks (a.k.a. deep learning). The book is fabulous. I cannot say enough good things about the book and the author. I knew nothing about neural networks prior to reading this book. As I said, my math skills are terribly rusty, but the author works through the math portions with tremendous patience. I am currently on page 92 and haven’t seen any programming stuff. Why? Because the author is first laying down the foundations. Then the programs will be built on top of solid concepts.I highly, highly recommend this book.

I cannot adequately describe my love for this book. I have several years of ML experience but decided recently to re-learn the fundamentals of neural nets for the sake of refreshing that which I have come to overlook or take for granted (this happens, seriously!). What an incredible pleasure it has been to explore this resource! The author does an amazing job of deconstructing the intuition behind neural networks and demystifies the assumptions or fears typically associated with them (probably because he avoids using jargon, which most authors do to veil their lack of understanding of subjects). Do not let past experience with neural nets engender a sense of snobbery when reading a book that might be seen as introductory—I recommend this book for people of all levels of expertise!Any 1 star review is either by those who have purchased the Kindle version (I have not experienced this personally but from the reviews posted would advise people AGAINST purchasing it) or probably by bitter competitors. Contrary to a few acerbic comments I've seen, I have no affiliation with the author except for a shared love of both ML and pedagogy. Thank you, Mr. Rashid, for this truly special resource. I will be passing this along to friends and colleague with my highest recommendation!

Good for learning

I liked the way this book has been structured. The content has been designed and explained in a way that anyone with a basic understanding of Calculus can begin their journey in the world of deep learning. Great starter book. Kudos to Tariq Rashid!!!

Author does a great job of explaining how neural networks function , and teaching you how to build your own. Once you've built it you quickly realise its strengths and limitations - NNs are good at correlation, but not new insights. Their ideal use case is repetitive classification tasks with uniform data.

neural network について興味はあるけど、何だかどの本も難し（めんどくさ）そうだなと思っている人には「買い」でしょう。この本は neural network の基礎的理論を解説し、さらに手書き数字の識別ができる neural network のコードを一歩ずつ python を使って書いていくという本です。私は kindle 版を買いました。amazon.com の review の高い評価と、kindle 版の値段（信じられない！）を考えると躊躇する理由はありませんでした。実際、neural network の理論の説明にしても、 python のコードの説明にしても、実に丁寧で驚きました。私自身は neural network の理論に使われている程度の数学には不自由しませんが、この著者は微分や行列の積まで丁寧に説明しています。高校生くらいでも十分理解できるのではないかと思います。決してレベルが低いわけではないと思います。もちろん、何でも書いてあるわけではありません。しっかりとした目標があって、その目標を達成するために必要なことをきちんとわからせてくれます。そして、（中身がちゃんとわかっている） python のコードが手元で動いて、手書き数字を識別してくれるのを見るのは、やはり面白いです。この python のコードもコンパクトで、こんな短いコードでできちゃうんだ、っていうのも（python をあまりよく知らなかった私には）収穫でした。

ディープラーニングを少しでも理解したいと思い、いろいろなドキュメントを漁って見ていますが、難しい数式だらけで敷居が高いものばかり。「ゼロから作るDeep Learning」も誤差逆伝搬法の章で頓挫。この本をたまたま見つけて読んでみたところ、かなり判った気になれました。満足。