دانلود کتاب Deep Learning: A Comprehensive Guide

فهرست مطالب :

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
The Authors
Chapter 1 Introduction to Deep Learning
Learning Objectives
1.1 Introduction
1.2 The Need: Why Deep Learning?
1.3 What Is the Need of a Transition From Machine Learning to Deep Learning?
1.4 Deep Learning Applications
1.4.1 Self-Driving Cars
1.4.2 Emotion Detection
1.4.3 Natural Language Processing
1.4.4 Entertainment
1.4.5 Healthcare
YouTube Session On Deep Learning Applications
Key Points to Remember
Quiz
Further Reading
Chapter 2 The Tools and the Prerequisites
Learning Objectives
2.1 Introduction
2.2 The Tools
2.2.1 Python Libraries – Must Know
2.2.2 The Installation Phase
A. Anaconda Installation
B. Jupyter Installation
C. The First Program With the Jupyter
D. Keras Installation
2.3 Datasets – A Quick Glance
Key Points to Remember
Quiz
Chapter 3 Machine Learning: The Fundamentals
Learning Objectives
3.1 Introduction
3.2 The Definitions – Yet Another Time
3.3 Machine Learning Algorithms
3.3.1 Supervised Learning Algorithms
3.3.2 The Unsupervised Learning Algorithms
3.3.3 Reinforcement Learning
3.3.4 Evolutionary Approach
3.4 How/Why Do We Need ML?
3.5 The ML Framework
3.6 Linear Regression – A Complete Understanding
3.7 Logistic Regression – A Complete Understanding
3.8 Classification – A Must-Know Concept
3.8.1 SVM – Support Vector Machines
3.8.2 K-NN (K-Nearest Neighbor)
3.9 Clustering – An Interesting Concept to Know
3.9.1 K-Means Clustering
Key Points to Remember
Quiz
Further Reading
Chapter 4 The Deep Learning Framework
Learning Objectives
4.1 Introduction
4.2 Artificial Neuron
4.2.1 Biological Neuron
4.2.2 Perceptron
4.2.2.1 How a Perceptron Works?
4.2.3 Activation Functions
4.2.4 Parameters
4.2.5 Overfitting
4.3 A Few More Terms
4.4 Optimizers
Key Points to Remember
Quiz
Further Reading
Chapter 5 CNN – Convolutional Neural Networks: A Complete Understanding
Learning Objectives
5.1 Introduction
5.2 What Is Underfitting, Overfitting and Appropriate Fitting?
5.3 Bias/variance – A Quick Learning
5.4 Convolutional Neural Networks
5.4.1 How Convolution Works
5.4.2 How Zero Padding Works
5.4.3 How Max Pooling Works
5.4.4 The CNN Stack – Architecture
5.4.5 What Is the Activation Function?
5.4.5.1 Sigmoid Activation Function
5.4.5.2 ReLU – Rectified Linear Unit
5.4.6 CNN – Model Building – Step By Step
Key Points to Remember
Quiz
Further Reading
Chapter 6 CNN Architectures: An Evolution
Learning Objectives
6.1 Introduction
6.2 LeNET CNN Architecture
6.3 VGG16 CNN Architecture
6.4 AlexNet CNN Architecture
6.5 Other CNN Architectures at a Glance
Key Points to Remember
Quiz
Further Reading
Chapter 7 Recurrent Neural Networks
Learning Objectives
7.1 Introduction
7.2 CNN vs. RNN: A Quick Understanding
7.3 RNN vs. Feedforward Neural Networks: A Quick Understanding
7.4 Simple RNN
7.5 LSTM: Long SHORT-TERM Memory
7.6 Gated Recurrent Unit
Key Points to Remember
Quiz
Further Reading
Chapter 8 Autoencoders
Learning Objectives
8.1 Introduction
8.2 What Is an Autoencoder?
8.2.1 How Autoencoders Work
8.2.2 Properties of Autoencoders
8.3 Applications of Autoencoders
8.3.1 Data Compression and Dimensionality Reduction
8.3.2 Image Denoising
8.3.3 Feature Extraction
8.3.4 Image Generation
8.3.5 Image Colorization
8.4 Types of Autoencoders
8.4.1 Denoising Autoencoder
8.4.2 Vanilla Autoencoder
8.4.3 Deep Autoencoder
8.4.4 Sparse Autoencoder
8.4.5 Undercomplete Autoencoder
8.4.6 Stacked Autoencoder
8.4.7 Variational Autoencoder (VAEs)
8.4.8 Convolutional Autoencoder
Key Points to Remember
Quiz
Further Reading
Chapter 9 Generative Models
Learning Objectives
9.1 Introduction
9.2 What Is a Generative Model?
9.3 What Are Generative Adversarial Networks (GAN)?
9.4 Types of GAN
9.4.1 Deep Convolutional GANs (DCGANs)
9.4.2 Stack GAN
9.4.3 Cycle GAN
9.4.4 Conditional GAN (CGAN)
9.4.5 Info GAN
9.5 Applications of GAN
9.5.1 Fake Image Generation
9.5.2 Image Modification
9.5.3 Text to Image/Image to Image Generation
9.5.4 Speech Modification
9.5.5 Assisting Artists
9.6 Implementation of GAN
Key Points to Remember
Quiz
Further Reading
Chapter 10 Transfer Learning
Learning Objectives
10.1 What Is Transfer Learning?
10.2 When Can We Use Transfer Learning?
10.3 Example – 1: Cat Or Dog Using Transfer Learning With VGG 16
10.4 Example – 2: Identify Your Relatives’ Faces Using Transfer Learning
10.5 The Difference Between Transfer Learning and Fine Tuning
10.6 Transfer Learning Strategies
10.6.1 Same Domain, Task
10.6.2 Same Domain, Different Task
10.6.3 Different Domain, Same Task
Key Points to Remember
Quiz
Further Reading
Chapter 11 Intel OpenVino: A Must-Know Deep Learning Toolkit
Learning Objectives
11.1 Introduction
11.2 OpenVino Installation Guidelines
Key Points to Remember
Quiz
Further Reading
Chapter 12 Interview Questions and Answers
Learning Objectives
YouTube Sessions On Deep Learning Applications
Index