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.

Preface

Introduction

Concept of this book

Acknowledgments

Free Chapter

1. Introduction to Python

1. Introduction to Python

What is Python?

Installing Python

Python Interpreter

Python Script Files

2. Perceptrons

What Is a Perceptron?

Simple Logic Circuits

Implementing Perceptrons

Limitations of Perceptrons

Multilayer Perceptrons

From NAND to a Computer

3. Neural Networks

3. Neural Networks

From Perceptrons to Neural Networks

Activation Function

Calculating Multidimensional Arrays

Implementing a Three-Layer Neural Network

Designing the Output Layer

Identity Function and Softmax Function

Handwritten Digit Recognition

4. Neural Network Training

4. Neural Network Training

Learning from Data

Numerical Differentiation

Implementing a Training Algorithm

5. Backpropagation

5. Backpropagation

Computational Graphs

Backward Propagation

Implementing a Simple Layer

Implementing the Activation Function Layer

Implementing the Affine and Softmax Layers

Implementing Backpropagation

6. Training Techniques

6. Training Techniques

Updating Parameters

Initial Weight Values

Validating Hyperparameters

7. Convolutional Neural Networks

7. Convolutional Neural Networks

Overall Architecture

The Convolution Layer

The Pooling Layer

Implementing the Convolution and Pooling Layers

Implementing a CNN

Visualizing a CNN

8. Deep Learning

8. Deep Learning

Making a Network Deeper

A Brief History of Deep Learning

Accelerating Deep Learning

Practical Uses of Deep Learning

The Future of Deep Learning

Appendix A

Computational Graph of the Softmax-with-Loss Layer

Customer Reviews

5 (1)

5 star

100%

4 star

0

3 star

0

2 star

0

1 star

0

What Is a Perceptron?

A perceptron receives multiple signals as inputs and outputs one signal. The "signal" here "flows" like an electric current or a river. In the same way that an electric current flows through a conductor and pushes electrons forward, the signal in a perceptron makes flow and transfers information. Unlike an electric current, the signal in a perceptron is binary: "Flow (1) or Do not flow (0)." In this book, 0 indicates "do not flow a signal" and 1 indicates "flow a signal."

(In the interest of precision, note that the perceptron described in this chapter is more accurately called an "artificial neuron" or a "simple perceptron." Here, we will call it a "perceptron" because the basic processes are often the same.)

Figure 2.1 shows an example of a perceptron that receives two signals as input:

Figure 2.1: Perceptron with two inputs

x1 and x2 are input signals...