Neural Networks and Deep learning_#1

About

Neural networks is one of the most beautiful programming paradigms ever invented. In the conventional approach to programming, we'll tell the computer, "What to do," breaking big problems up into many small, PR Ecisely defined tasks that the computer can easily perform. By contrast, in a neural network we don't tell the computer what the solve our problem. Instead, it learns from observational data, figuring out its own solution to the problem at hand.

  automatically learning from data sounds promising. However, until 2006 we didn ' t know how to train neural networks to surpass more traditional approaches, except for a few s pecialized problems. What changed in 2006 is the discovery of techniques for learning in so-called deep neural networks. These techniques is now known as deep learning. They ' ve been developed further, and today deep neural networks and deep learning achieve outstanding performance on many I mportant problems in computer vision, speech recognition, and natural language processing. They ' re being deployed on a large scale by companies such as Google, Microsoft, and Facebook.

The purpose of the "is" to "help you Master" the core concepts of neural networks, including modern techniques for deep Learning. After working through the book, you'll have written code, uses neural networks and deep learning to solve complex pat Tern recognition problems. And you'll have a foundation for use neural networks and deep learning to attack problems of your own devising.

A principle-oriented Approach

One conviction underlying the book was that it's better to obtain a solid understanding of the core principles of neural Networks and deep learning, rather than a hazy understanding of a long laundry list of ideas. If You've understood the core ideas well, you can rapidly understand and other new material. In programming language terms, think of it as mastering the core syntax, libraries and data structures of a new language. Still only "know" a tiny fraction of the total Language-many languages has enormous standard libraries-but NE w libraries and data structures can be understood quickly and easily.

This means the book was emphatically not a tutorial-in-use some particular neural network library. If you mostly want to learn your A-a library, don ' t read this around Find the library you wish to learn, and work through the tutorials and documentation. But being warned. While this have an immediate problem-solving payoff, if you want to understand what's really going on neural networks, I f you want insights that would still be relevant years from now and then it's not enough just to learn some hot library. You need to understand the durable, lasting insights underlying what neural networks work. Technologies come and Technologies go, but insight is forever.

A Hands-on approach

We ll learn the core principles behind neural networks and deep learning by attacking a concrete problem:the problem O F Teaching a computer to recognize handwritten digits. This problem was extremely difficult to solve using the conventional approach to programming. And yet, as we'll see, it can is solved pretty well using a simple neural network with just a few tens of lines of code, and no special libraries. What's more, we'll improve the program through many iterations, gradually incorporating more and more of the core ideas AB Out neural networks and deep learning.

This hands-on approach means, you'll need some programming experience to read the book. But you don ' t need to be a professional programmer. I ' ve written the code in Python (version 2.7), which, even if you don ' t program in Python, should is easy to understand WI Th just a little effort. Through The course of the book we'll develop a little neural network library, which you can use for experiment and to Bui LD understanding. All the code was available for Download here. Once you ' ve finished the book, or as a read it, you can easily pick up one of the more Feature-complete neural network l Ibraries intended for use in production.

On a related note, the mathematical requirements to read the book is modest. There is some mathematics in the most chapters, but it's usually just elementary algebra and plots of functions, which I ExPEC T most readers would be okay with. I occasionally use more advanced mathematics, but has structured the material so can follow even if some mathematical Details elude you. The one chapter which uses heavier mathematics extensively Is chapter 2, which requires a little multivariable calcul US and linear algebra. If those aren ' t familiar, I begin chapter 2 with A discussion of how to navigate the mathematics. If you're finding it really heavy going, you can simply skip to the summary of the chapter ' s main results. In any case, there's no need to worry on the outset.

It's rare for a book to aim both principle-oriented and hands-on. But I believe you'll learn best if we build out the fundamental ideas of neural networks. We ' ll develop living code, not just abstract theory, code which you can explore and extend. This is the understand the fundamentals, both in theory and practice, and is well set to add further to your knowledge .

Neural Networks and Deep learning_#1