
Principles and Labs for Deep Learning
- 1st Edition - June 25, 2021
- Imprint: Academic Press
- Authors: Shih-Chia Huang, Trung-Hieu Le
- Language: English
- Paperback ISBN:9 7 8 - 0 - 3 2 3 - 9 0 1 9 8 - 7
- eBook ISBN:9 7 8 - 0 - 3 2 3 - 9 0 1 9 9 - 4
Principles and Labs for Deep Learning provides the knowledge and techniques needed to help readers design and develop deep learning models. Deep Learning techniques are introduce… Read more

Purchase options

Institutional subscription on ScienceDirect
Request a sales quotePrinciples and Labs for Deep Learning provides the knowledge and techniques needed to help readers design and develop deep learning models. Deep Learning techniques are introduced through theory, comprehensively illustrated, explained through the TensorFlow source code examples, and analyzed through the visualization of results. The structured methods and labs provided by Dr. Huang and Dr. Le enable readers to become proficient in TensorFlow to build deep Convolutional Neural Networks (CNNs) through custom APIs, high-level Keras APIs, Keras Applications, and TensorFlow Hub. Each chapter has one corresponding Lab with step-by-step instruction to help the reader practice and accomplish a specific learning outcome.
Deep Learning has been successfully applied in diverse fields such as computer vision, audio processing, robotics, natural language processing, bioinformatics and chemistry. Because of the huge scope of knowledge in Deep Learning, a lot of time is required to understand and deploy useful, working applications, hence the importance of this new resource. Both theory lessons and experiments are included in each chapter to introduce the techniques and provide source code examples to practice using them. All Labs for this book are placed on GitHub to facilitate the download. The book is written based on the assumption that the reader knows basic Python for programming and basic Machine Learning.
- Introduces readers to the usefulness of neural networks and Deep Learning methods
- Provides readers with in-depth understanding of the architecture and operation of Deep Convolutional Neural Networks
- Demonstrates the visualization needed for designing neural networks
- Provides readers with an in-depth understanding of regression problems, binary classification problems, multi-category classification problems, Variational Auto-Encoder, Generative Adversarial Network, and Object detection
- Cover image
- Title page
- Table of Contents
- Copyright
- Preface
- Environment installation
- Abstract
- 1: Python installation
- 2: TensorFlow installation
- 3: Python extension installation
- 4: Jupyter notebook
- 5: PyCharm IDE
- 6: GitHub labs
- Chapter 1: Introduction to TensorFlow 2
- Abstract
- 1.1: Deep learning
- 1.2: Introduction to TensorFlow
- 1.3: Improvement of TensorFlow 2
- 1.4: Eager execution
- 1.5: Keras
- 1.6: Tf.data
- Chapter 2: Neural networks
- Abstract
- 2.1: Introduction to neural networks
- 2.2: Introduction to Kaggle
- 2.3: Experiment 1: House price prediction
- 2.4: Introduction to TensorBoard
- 2.5: Experiment 2: Overfitting problem
- Chapter 3: Binary classification problem
- Abstract
- 3.1: Machine learning algorithms
- 3.2: Binary classification problem
- 3.3: Experiment: Pokémon combat prediction
- Chapter 4: Multi-category classification problem
- Abstract
- 4.1: Convolutional neural network
- 4.2: Multi-category classification
- 4.3: Experiment: CIFAR-10 image classification
- Chapter 5: Training neural network
- Abstract
- 5.1: Backpropagation
- 5.2: Weight initialization
- 5.3: Batch normalization
- 5.4: Experiment 1: Verification of three weight initialization methods
- 5.5: Experiment 2: Verification of batch normalization
- 5.6: Comparison of different neural networks
- Chapter 6: Advanced TensorFlow
- Abstract
- 6.1: Advanced TensorFlow
- 6.2: Using high-level keras API and custom API of TensorFlow
- 6.3: Experiment: implementation of two network models using high-level keras API and custom API
- Chapter 7: Advanced TensorBoard
- Abstract
- 7.1: Advanced TensorBoard
- 7.2: Experiment 1: Using tf.summary.image API to visualize training results
- 7.3: Experiment 2: Hyperparameter tuning with TensorBoard HParams
- Chapter 8: Convolutional neural network architectures
- Abstract
- 8.1: Popular convolutional neural network architectures
- 8.2: Experiment: Implementation of inception-v3 network
- Chapter 9: Transfer learning
- Abstract
- 9.1: Transfer learning
- 9.2: Experiment: Using Inception-v3 for transfer learning
- Chapter 10: Variational auto-encoder
- Abstract
- 10.1: Introduction to auto-encoder
- 10.2: Introduction to variational auto-encoder
- 10.3: Experiment: Implementation of variational auto-encoder model
- Chapter 11: Generative adversarial network
- Abstract
- 11.1: Generative adversarial network
- 11.2: Introduction to WGAN-GP
- 11.3: Experiment: Implementation of WGAN-GP
- Chapter 12: Object detection
- Abstract
- 12.1: Computer vision
- 12.2: Introduction to object detection
- 12.3: Object detection methods
- 12.4: Experiment: Implementation of YOLO-v3
- Index
- Edition: 1
- Published: June 25, 2021
- No. of pages (Paperback): 366
- No. of pages (eBook): 366
- Imprint: Academic Press
- Language: English
- Paperback ISBN: 9780323901987
- eBook ISBN: 9780323901994
SH
Shih-Chia Huang
TL