Make Your Own Neural Network: An In-depth Visual Introduction For Beginners

Michael Taylor

  • 出版商: Independently published
  • 出版日期: 2017-10-04
  • 售價: $580
  • 貴賓價: 9.5$551
  • 語言: 英文
  • 頁數: 248
  • 裝訂: Paperback
  • ISBN: 1549869132
  • ISBN-13: 9781549869136
  • 相關分類: DeepLearning
  • 立即出貨(限量) (庫存=1)

買這商品的人也買了...

商品描述

A step-by-step visual journey through the mathematics of neural networks, and making your own using Python and Tensorflow.

 

What you will gain from this book:

* A deep understanding of how a Neural Network works. * How to build a Neural Network from scratch using Python.

Who this book is for:

* Beginners who want to fully understand how networks work, and learn to build two step-by-step examples in Python. * Programmers who need an easy to read, but solid refresher, on the math of neural networks.

What’s Inside - ‘Make Your Own Neural Network: An Indepth Visual Introduction For Beginners’

What Is a Neural Network?

Neural networks have made a gigantic comeback in the last few decades and you likely make use of them everyday without realizing it, but what exactly is a neural network? What is it used for and how does it fit within the broader arena of machine learning?

we gently explore these topics so that we can be prepared to dive deep further on. To start, we’ll begin with a high-level overview of machine learning and then drill down into the specifics of a neural network.

The Math of Neural Networks

On a high level, a network learns just like we do, through trial and error. This is true regardless if the network is supervised, unsupervised, or semi-supervised. Once we dig a bit deeper though, we discover that a handful of mathematical functions play a major role in the trial and error process. It also becomes clear that a grasp of the underlying mathematics helps clarify how a network learns.

* Forward Propagation * Calculating The Total Error * Calculating The Gradients * Updating The Weights

Make Your Own Artificial Neural Network: Hands on Example

You will learn to build a simple neural network using all the concepts and functions we learned in the previous few chapters. Our example will be basic but hopefully very intuitive. Many examples available online are either hopelessly abstract or make use of the same data sets, which can be repetitive. Our goal is to be crystal clear and engaging, but with a touch of fun and uniqueness. This section contains the following eight chapters.

Building Neural Networks in Python

There are many ways to build a neural network and lots of tools to get the job done. This is fantastic, but it can also be overwhelming when you start, because there are so many tools to choose from. We are going to take a look at what tools are needed and help you nail down the essentials. To build a neural network

Tensorflow and Neural Networks

There is no single way to build a feedforward neural network with Python, and that is especially true if you throw Tensorflow into the mix. However, there is a general framework that exists that can be divided into five steps and grouped into two parts. We are going to briefly explore these five steps so that we are prepared to use them to build a network later on. Ready? Let’s begin.

Neural Network: Distinguish Handwriting

We are going to dig deep with Tensorflow and build a neural network that can distinguish between handwritten numbers. We’ll use the same 5 steps we covered in the high-level overview, and we are going to take time exploring each line of code.

Neural Network: Classify Images

10 minutes. That’s all it takes to build an image classifier thanks to Google! We will provide a high-level overview of how to classify images using a convolutional neural network (CNN) and Google’s Inception V3 model. Once finished, you will be able to tweak this code to classify any type of image sets! Cats, bats, super heroes - the sky’s the limit.

商品描述(中文翻譯)

這本書是一本透過視覺化方式逐步介紹神經網絡數學原理的書籍,並使用Python和Tensorflow來建立自己的神經網絡。

這本書將帶給你以下收穫:
- 對神經網絡的運作原理有深入的理解。
- 學習如何使用Python從頭開始建立神經網絡。

這本書適合以下讀者:
- 想要完全理解網絡運作方式並學習如何在Python中逐步建立兩個示例的初學者。
- 需要對神經網絡數學知識進行輕鬆閱讀但堅實複習的程式設計師。

書中內容包括:
- 什麼是神經網絡?
- 神經網絡的數學原理,包括前向傳播、計算總誤差、計算梯度和更新權重。
- 以實際範例建立自己的人工神經網絡。
- 使用Python建立神經網絡的方法和工具。
- 使用Tensorflow建立前饋神經網絡的步驟。
- 使用Tensorflow建立可以辨識手寫數字的神經網絡。
- 使用Tensorflow建立圖像分類器的神經網絡。

這本書將帶領讀者深入了解神經網絡的數學原理,並提供實際範例和使用Python和Tensorflow建立神經網絡的方法。無論你是初學者還是有經驗的程式設計師,這本書都能幫助你理解和應用神經網絡的知識。