Book Image

Deep Learning from the Basics

By : Koki Saitoh
5 (1)
Book Image

Deep Learning from the Basics

5 (1)
By: Koki Saitoh

Overview of this book

Deep learning is rapidly becoming the most preferred way of solving data problems. This is thanks, in part, to its huge variety of mathematical algorithms and their ability to find patterns that are otherwise invisible to us. Deep Learning from the Basics begins with a fast-paced introduction to deep learning with Python, its definition, characteristics, and applications. You’ll learn how to use the Python interpreter and the script files in your applications, and utilize NumPy and Matplotlib in your deep learning models. As you progress through the book, you’ll discover backpropagation—an efficient way to calculate the gradients of weight parameters—and study multilayer perceptrons and their limitations, before, finally, implementing a three-layer neural network and calculating multidimensional arrays. By the end of the book, you’ll have the knowledge to apply the relevant technologies in deep learning.
Table of Contents (11 chapters)

Installing Python

The following section describes some precautions you will need to take when installing Python in your environment (PC).

Python Versions

Python has two major versions: version 2 and version 3. Currently, both are in active use. So, when you install Python, you must carefully choose which version to install. These two versions are not completely compatible (to be accurate, no backward compatibility is available). Some programs written in Python 3 cannot be run in Python 2. This book uses Python 3. If you have only Python 2 installed, installing Python 3 is recommended.

External Libraries That We Use

The goal of this book is to implement Deep Learning from the Basics. So, our policy is that we will use external libraries as little as possible, but we will use the following two libraries by way of exception: NumPy and Matplotlib. We will use these two libraries to implement deep learning efficiently.

NumPy is a library for numerical calculations. It provides many convenient methods for handling advanced mathematical algorithms and arrays (matrices). To implement deep learning in this book, we will use these convenient methods for efficient implementation.

Matplotlib is a library for drawing graphs. You can use Matplotlib to visualize experimental results and visually check the data while executing deep learning. This book uses these libraries to implement deep learning.

This book uses the following programming language and libraries:

  • Python 3
  • NumPy
  • Matplotlib

Now, we will describe how to install Python for those who need to install it. If you have already met these requirements, you can skip this section.

Anaconda Distribution

Although numerous methods are available for installing Python, this book recommends that you use a distribution called Anaconda. Distributions contain the required libraries so that the user can install them collectively. The Anaconda distribution focuses on data analysis. It also contains libraries useful for data analysis, such as NumPy and Matplotlib, as described earlier.

As we mentioned previously, this book uses Python 3. Therefore, you will need to install the Anaconda distribution for Python 3. Use the following link to download the distribution suitable for your OS and install it:

https://docs.anaconda.com/anaconda/install/