Deep Learning: A Comprehensive Guide provides comprehensive coverage of Deep Learning (DL) and Machine Learning (ML) concepts. DL and ML are the most sought-after domains, requiring a deep understanding and this book gives no less than that. This book enables the reader to build innovative and useful applications based on ML and DL. Starting with the basics of neural networks, and continuing through the architecture of various types of CNNs, RNNs, LSTM, and more till the end of the book, each and every topic is given the utmost care and shaped professionally and comprehensively.
Key Features
Includes the smooth transition from ML concepts to DL concepts
Line-by-line explanations have been provided for all the coding-based examples
Includes a lot of real-time examples and interview questions that will prepare the reader to take up a job in ML/DL right away
Even a person with a non-computer-science background can benefit from this book by following the theory, examples, case studies, and code snippets
Every chapter starts with the objective and ends with a set of quiz questions to test the readers understanding
Includes references to the related YouTube videos that provide additional guidance
AI is a domain for everyone. This book is targeted toward everyone irrespective of their field of specialization. Graduates and researchers in deep learning will find this book useful.
| Preface |
|
xi | |
| The Authors |
|
xiii | |
|
Chapter 1 Introduction to Deep Learning |
|
|
1 | (12) |
|
|
|
1 | (1) |
|
1.2 The Need: Why Deep Learning? |
|
|
2 | (1) |
|
1.3 What Is The Need Of A Transition From Machine Learning To Deep Learning? |
|
|
2 | (2) |
|
1.4 Deep Learning Applications |
|
|
4 | (5) |
|
|
|
4 | (1) |
|
|
|
5 | (1) |
|
1.4.3 Natural Language Processing |
|
|
5 | (2) |
|
|
|
7 | (1) |
|
|
|
8 | (1) |
|
Youtube Session On Deep Learning Applications |
|
|
9 | (1) |
|
|
|
9 | (1) |
|
|
|
10 | (1) |
|
|
|
10 | (3) |
|
Chapter 2 The Tools and the Prerequisites |
|
|
13 | (16) |
|
|
|
13 | (1) |
|
|
|
14 | (13) |
|
2.2.1 Python Libraries -- Must Know |
|
|
14 | (2) |
|
2.2.2 The Installation Phase |
|
|
16 | (11) |
|
2.3 Datasets -- A Quick Glance |
|
|
27 | (1) |
|
|
|
28 | (1) |
|
|
|
28 | (1) |
|
Chapter 3 Machine Learning: The Fundamentals |
|
|
29 | (36) |
|
|
|
29 | (1) |
|
3.2 The Definitions -- Yet Another Time |
|
|
30 | (1) |
|
3.3 Machine Learning Algorithms |
|
|
31 | (5) |
|
3.3.1 Supervised Learning Algorithms |
|
|
31 | (2) |
|
3.3.2 The Unsupervised Learning Algorithms |
|
|
33 | (2) |
|
3.3.3 Reinforcement Learning |
|
|
35 | (1) |
|
3.3.4 Evolutionary Approach |
|
|
36 | (1) |
|
3.4 Howavhy Do We Need Ml? |
|
|
36 | (1) |
|
|
|
37 | (2) |
|
3.6 Linear Regression -- A Complete Understanding |
|
|
39 | (10) |
|
3.7 Logistic Regression -- A Complete Understanding |
|
|
49 | (1) |
|
3.8 Classification -- A Must-Know Concept |
|
|
50 | (7) |
|
3.8.1 SVM -- Support Vector Machines |
|
|
50 | (3) |
|
3.8.2 K-NN (K-Nearest Neighbor) |
|
|
53 | (4) |
|
3.9 Clustering -- An Interesting Concept To Know |
|
|
57 | (5) |
|
|
|
58 | (4) |
|
|
|
62 | (1) |
|
|
|
63 | (1) |
|
|
|
63 | (2) |
|
Chapter 4 The Deep Learning Framework |
|
|
65 | (16) |
|
|
|
65 | (1) |
|
|
|
66 | (9) |
|
|
|
66 | (1) |
|
|
|
67 | (1) |
|
4.2.2.7 How a Perceptron Works? |
|
|
68 | (1) |
|
4.2.3 Activation Functions |
|
|
69 | (3) |
|
|
|
72 | (2) |
|
|
|
74 | (1) |
|
|
|
75 | (1) |
|
|
|
75 | (2) |
|
|
|
77 | (1) |
|
|
|
78 | (1) |
|
|
|
78 | (3) |
|
Chapter 5 CNN -- Convolutional Neural Networks: A Complete Understanding |
|
|
81 | (40) |
|
|
|
82 | (1) |
|
5.2 What Is Underfitting, Overfitting And Appropriate Fitting? |
|
|
82 | (2) |
|
5.3 Biasa/Ariance-A Quick Learning |
|
|
84 | (1) |
|
5.4 Convolutional Neural Networks |
|
|
84 | (34) |
|
5.4.1 How Convolution Works |
|
|
88 | (9) |
|
5.4.2 How Zero Padding Works |
|
|
97 | (9) |
|
5.4.3 How Max Pooling Works |
|
|
106 | (3) |
|
5.4.4 The CNN Stack -- Architecture |
|
|
109 | (1) |
|
5.4.5 What Is the Activation Function? |
|
|
110 | (1) |
|
5.4.5.1 Sigmoid Activation Function |
|
|
110 | (1) |
|
5.4.5.2 ReLU -- Rectified Linear Unit |
|
|
111 | (1) |
|
5.4.6 CNN -- Model Building -- Step by Step |
|
|
111 | (7) |
|
|
|
118 | (1) |
|
|
|
119 | (1) |
|
|
|
119 | (2) |
|
Chapter 6 CNN Architectures: An Evolution |
|
|
121 | (36) |
|
|
|
121 | (1) |
|
6.2 Lenet Cnn Architecture |
|
|
122 | (11) |
|
6.3 Vgg16 Cnn Architecture |
|
|
133 | (8) |
|
6.4 Alexnet Cnn Architecture |
|
|
141 | (8) |
|
6.5 Other Cnn Architectures At A Glance |
|
|
149 | (5) |
|
|
|
154 | (1) |
|
|
|
154 | (1) |
|
|
|
155 | (2) |
|
Chapter 7 Recurrent Neural Networks |
|
|
157 | (28) |
|
|
|
157 | (3) |
|
7.2 Cnn Vs. Rnn: A Quick Understanding |
|
|
160 | (1) |
|
7.3 Rnn Vs. Feedforward Neural Networks: A Quick Understanding |
|
|
161 | (3) |
|
|
|
164 | (2) |
|
7.5 Lstm: Long Short-Term Memory |
|
|
166 | (10) |
|
|
|
176 | (6) |
|
|
|
182 | (1) |
|
|
|
182 | (1) |
|
|
|
183 | (2) |
|
|
|
185 | (24) |
|
|
|
185 | (1) |
|
8.2 What Is An Autoencoder? |
|
|
186 | (5) |
|
8.2.1 How Autoencoders Work |
|
|
186 | (4) |
|
8.2.2 Properties of Autoencoders |
|
|
190 | (1) |
|
8.3 Applications Of Autoencoders |
|
|
191 | (1) |
|
8.3.1 Data Compression and Dimensionality Reduction |
|
|
191 | (1) |
|
|
|
191 | (1) |
|
|
|
192 | (1) |
|
|
|
192 | (1) |
|
|
|
192 | (1) |
|
8.4 Types Of Autoencoders |
|
|
192 | (13) |
|
8.4.1 Denoising Autoencoder |
|
|
193 | (1) |
|
8.4.2 Vanilla Autoencoder |
|
|
193 | (1) |
|
|
|
194 | (1) |
|
|
|
194 | (1) |
|
8.4.5 Undercomplete Autoencoder |
|
|
195 | (1) |
|
8.4.6 Stacked Autoencoder |
|
|
195 | (1) |
|
8.4.7 Variational Autoencoder (VAEs) |
|
|
195 | (1) |
|
8.4.8 Convolutional Autoencoder |
|
|
196 | (9) |
|
|
|
205 | (1) |
|
|
|
206 | (1) |
|
|
|
207 | (2) |
|
Chapter 9 Generative Models |
|
|
209 | (18) |
|
|
|
209 | (1) |
|
9.2 What Is A Generative Model? |
|
|
210 | (1) |
|
9.3 What Are Generative Adversarial Networks (Can)? |
|
|
211 | (2) |
|
|
|
213 | (2) |
|
9.4.1 Deep Convolutional GANs (DCGANs) |
|
|
213 | (1) |
|
|
|
214 | (1) |
|
|
|
214 | (1) |
|
9.4.4 Conditional GAN (cGAN) |
|
|
214 | (1) |
|
|
|
214 | (1) |
|
|
|
215 | (2) |
|
9.5.1 Fake Image Generation |
|
|
215 | (1) |
|
|
|
215 | (1) |
|
9.5.3 Text to Image/Image to Image Generation |
|
|
215 | (1) |
|
9.5.4 Speech Modification |
|
|
215 | (1) |
|
|
|
215 | (2) |
|
9.6 Implementation Of Gan |
|
|
217 | (7) |
|
|
|
224 | (1) |
|
|
|
224 | (1) |
|
|
|
224 | (3) |
|
Chapter 10 Transfer Learning |
|
|
227 | (18) |
|
10.1 What Is Transfer Learning? |
|
|
227 | (1) |
|
10.2 When Can We Use Transfer Learning? |
|
|
228 | (1) |
|
10.3 Example -- 1: Cat Or Dog Using Transfer Learning With Vgg 16 |
|
|
229 | (4) |
|
10.4 Example -- 2: Identify Your Relatives' Faces Using Transfer Learning |
|
|
233 | (6) |
|
10.5 The Difference Between Transfer Learning And Finetuning |
|
|
239 | (2) |
|
10.6 Transfer Learning Strategies |
|
|
241 | (1) |
|
|
|
242 | (1) |
|
10.6.2 Same Domain, Different Task |
|
|
242 | (1) |
|
10.6.3 Different Domain, Same Task |
|
|
242 | (1) |
|
|
|
242 | (1) |
|
|
|
243 | (1) |
|
|
|
243 | (2) |
|
Chapter 11 Intel OpenVino: A Must-Know Deep Learning Toolkit |
|
|
245 | (16) |
|
|
|
245 | (1) |
|
11.2 Openvino Installation Guidelines |
|
|
246 | (13) |
|
|
|
259 | (1) |
|
|
|
259 | (1) |
|
|
|
260 | (1) |
|
Chapter 12 Interview Questions and Answers |
|
|
261 | (28) |
|
Youtube Sessions On Deep Learning Applications |
|
|
288 | (1) |
| Index |
|
289 | |
Dr. Shriram K Vasudevan is an Academician with a blend of Industrial and Teaching experience for 15 years. Strongly passionate to take up challenging tasks. Authored / Co-Authored 42 books for reputed publishers across the globe. Authored 122 research papers in revered international journals, 30 Papers in international/national conferences. Currently working as Dean of K.Ramakrishnan College of Technology. He is a Fellow IETE, ACM Distinguished Speaker, CSI Distinguished Speaker, and Intel Software Innovator. He has a YouTube channel Shriram Vasudevan, through which he teaches thousands of people all around the world.
Recognized/awarded by Datastax, ACM, IETE, Proctor and Gamble Innovation Centre (India), Dinamalar, AWS (Amazon Web Services), Sabre Technologies, IEEE Compute, Syndicate Bank, MHRD, Elsevier, Bounce, IncubateInd, Smart India Hackathon, Stop the bleed, Hackharvard (Harvard University), Accenture Digital (India), NEC (Nippon Electric Company, Japan), Thought Factory (Axis Bank Innovation Lab), Rakuten (Japan), Titan, Future Group, Institution of Engineers of India (IEI), Ministry of Food Processing Industries (MoFPI Govt. of India), Intel, Microsoft, Wipro, Infosys, IBM India, SoS Ventures (USA), VIT University, Amrita University, Computer Society of India, TBI TIDE, ICTACT, Times of India, Nehru Group of institutions, Texas Instruments, IBC Cambridge, Cisco, CII (Confederation of Indian Industries), Indian Air Force, DPSRU Innovation & Incubation Foundation, ELGi Equipments (Coimbatore), etc. for his technical expertise. Listed in many famous biographical databases.
The notable honors are: First Indian to be selected as HDE (Huawei Developer Expert), NVIDIA Certified Deep Learning Instructor, Winner of the HARVARD University Hack Harvard Global 2019 World Hack 2019. Winner of 50 plus hackathons, Selected as "Intel IoT Innovator" and inducted into "Intel Software Innovator" group. Awarded "Top Innovator" award 2018, "Top Innovator Innovator Summit 2019", World Record Holder With Sister Subashri Vasudevan (Only Sibling in the Globe to have authored 9 books together, Unique World Record Books), Entry in Limca book of records for National Record 2015, Entry in India Book of Records National Record and Appreciation. 2017.
Ms. Siniraj Pulari is a Professor in a Government University in Bahrain with 14 years of experience in various reputed Indian universities and Industry by making contributions to the teaching field and carrying out activities to maintain and develop, research and professional activities relevant to Computer Science Engineering. Research interests include areas of Natural Language Processing, Recommender systems, Information Retrieval, Deep Learning and Machine Learning
Authored 17 plus Scopus Indexed Publications, Guided over 30+ UG and PG students for various innovative product based and algorithmic ideas, was an active member of the Funded Project -Early Warning and Monitoring System of Elephants - Amrita University, Member of International Association of Engineers (IAENG) and Computer Society of India (CSI). Delivered various invited lectures on the Applications and emerging trends in a variety of upcoming technological and research advancements. Actively participated to the board of studies. Organized, presented and participated various national and international Technical Events, Conferences, Workshops and Hackathons. Have been in the International Advisory committee of various International Conferences.
Ms. Subashri holds an M.Tech in CSE and was associated with Cognizant Technology solutions for around 8+ years before taking a break. She was working as a senior developer and has exposure to various DOTNET technologies and reporting tools. She has co authored 25+ technical books for reputed publishers across the world. Few of them include, Software Engineering, C# programming, C++ programming, etc. Her name is featured in the Limca book of records for the category - maximum number of books authored by siblings. She has recently developed an interest in the IoT and ML areas and started contributing to the projects involving these technologies. Teaching is her passion and she wants to make technology look simpler for the students. She also manages a technical YouTube (All about BI) channel for Azure related concepts and she has also delivered dozens of lectures in various educational institutions.
More info about Taylor & Francis e-books