Deep Learning for Engineers

✍ Scribed by Tariq M. Arif; Md Adilur Rahim

• Publisher: CRC Press
• Year: 2023
• Tongue: English
• Leaves: 170
• Category: Library

✦ Synopsis

Deep Learning for Engineers introduces the fundamental principles of deep learning along with an explanation of the basic elements required for understanding and applying deep learning models.

As a comprehensive guideline for applying deep learning models in practical settings, this book features an easy-to-understand coding structure using Python and PyTorch with an in-depth explanation of four typical deep learning case studies on image classification, object detection, semantic segmentation, and image captioning. The fundamentals of convolutional neural network (CNN) and recurrent neural network (RNN) architectures and their practical implementations in science and engineering are also discussed.

This book includes exercise problems for all case studies focusing on various fine-tuning approaches in deep learning. Science and engineering students at both undergraduate and graduate levels, academic researchers, and industry professionals will find the contents useful.

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Contents
About the Authors
Chapter 1: Introduction
Chapter 2: Basics of Deep Learning
2.1. BUILDING BLOCKS
2.1.1. Artificial Neural Networks
2.1.2. Types of Learning
2.1.3. Multi-Layer Perceptron
2.2. NEURONS AND ACTIVATION FUNCTIONS
2.2.1. Sigmoid Activation
2.2.2. Hyperbolic Tangent Activation
2.2.3. Rectified Linear Units (ReLU) Activation
2.2.4. Leaky Rectified Linear Unit (Leaky ReLU) Activation
2.2.5. Exponential Linear Units (ELU) Activation
2.2.6. SoftPlus Activation
2.3. INTRODUCING NONLINEARITY USING ACTIVATION FUNCTIONS
2.4. INITIALIZATION AND OPTIMIZATION
2.4.1. Weight Initialization
2.4.2. Weight Regularization
2.4.3. Optimizer
2.4.4. Batch Normalization
2.5. MINIMIZING THE LOSS FUNCTION
2.5.1. Gradient Descent Algorithm
2.6. FORWARD AND BACKPROPAGATION
2.7. HYPERPARAMETERS
2.7.1. Fine-Tuning Hyperparameters
2.7.2. Batch, Iteration, and Epoch
2.7.3. Cross-Validation
2.8. DEEP TRANSFER LEARNING
2.8.1. Types of Transfer Learning
2.8.2. Pre-Trained Networks
2.8.3. Feature Extraction and Data Augmentation
2.8.4. Model Evaluation
Chapter 3: Computer Vision Fundamentals
3.1. INTRODUCTION
3.2. CNN ARCHITECTURE
3.2.1. Input Layer
3.2.2. Convolutional Layer
3.2.3. Non-Linearity Layer
3.2.4. Pooling Layer
3.2.5. Fully Connected Layer
3.2.6. Output Layer
3.3. APPLICATIONS
3.3.1. Image Classification
3.3.2. Object Detection
3.3.3. Image Segmentation
3.3.4. Natural Language Processing (NLP)
3.3.5. Image Generation
Chapter 4: Natural Language Processing Fundamentals
4.1. INTRODUCTION
4.2. RNN ARCHITECTURE
4.2.1. Basic Structures
4.3. APPLICATIONS
4.3.1. Time-Series Forecasting
4.3.2. Text Processing
4.3.3. Speech Recognition
4.3.4. Gesture Recognition
4.3.5. Sentiment Analysis
4.4. OTHER DEEP LEARNING MODELS
Chapter 5: Deep Learning Framework Installation: Pytorch and Cuda
5.1. INTRODUCTION TO DEEP LEARNING FRAMEWORKS
5.2. ANACONDA INSTALLATION
5.3. SETTING UP ENVIRONMENT VARIABLES
5.4. INSTALL AND SETUP PYTORCH FRAMEWORK
5.4.1. CUDA and cuDNN Installation
5.5. SETUP OPENCV AND ADDITIONAL LIBRARIES
5.6. VERIFY CUDA SETUP
Chapter 6: Case Study I: Image Classification
6.1. PROBLEM STATEMENT
6.2. DEFINING DEFAULT CONFIGURATION
6.3. RANDOM SEED AND IMPORT MODULES/LIBRARIES
6.4. DEFINE DATASET CLASS AND ATTRIBUTES
6.5. LOAD DATASET AND MODEL ARCHITECTURE
6.6. TRAINING SETUP FOR MULTI-GPU WORKSTATION
6.7. MODEL TRAINING AND SAVING THE BEST MODEL
6.8. TRAINING SETUP FOR SINGLE GPU WORKSTATION
6.9. MODEL TESTING AND INFERENCE
6.9.1. Fine Tuning
6.9.2. Using a Different Optimizer
6.10. SIMILAR APPLICATIONS FOR ENGINEERS
6.11. EXERCISE PROBLEM
Chapter 7: Case Study II: Object Detection
7.1. PROBLEM STATEMENT
7.2. DEFINING DEFAULT CONFIGURATION
7.3. RANDOM SEED AND IMPORT MODULES/LIBRARIES
7.4. DEFINE DATASET CLASS AND ATTRIBUTES
7.5. LOAD DATASET AND MODEL ARCHITECTURE
7.6. MODEL TRAINING AND SAVING THE BEST MODEL
7.7. MODEL TESTING AND INFERENCE
7.7.1. Fine Tuning
7.8. SIMILAR APPLICATIONS FOR ENGINEERS
7.9. EXERCISE PROBLEM
Chapter 8: Case Study III: Semantic Segmentation
8.1. PROBLEM STATEMENT
8.2. DEFINING DEFAULT CONFIGURATION
8.3. RANDOM SEED AND IMPORT MODULES/LIBRARIES
8.4. DEFINE DATASET CLASS AND ATTRIBUTES
8.5. LOAD DATASET AND MODEL ARCHITECTURE
8.6. MODEL TRAINING AND SAVING THE BEST MODEL
8.7. MODEL TESTING AND INFERENCE
8.7.1. Fine Tuning
8.7.2. Using a Different Loss Function
8.8. SIMILAR APPLICATIONS FOR ENGINEERS
8.9. EXERCISE PROBLEM
Chapter 9: Case Study IV: Image Captioning
9.1. PROBLEM STATEMENT
9.2. DEFINING DEFAULT CONFIGURATION
9.3. RANDOM SEED AND IMPORT MODULES/LIBRARIES
9.4. TOKENIZE CAPTIONS
9.5. DEFINE DATASET CLASS AND ATTRIBUTES
9.6. LOAD DATASET AND MODEL ARCHITECTURE
9.6.1. Define Attention Mechanism
9.7. MODEL TRAINING AND SAVING THE BEST MODEL
9.8. MODEL TESTING AND INFERENCE
9.8.1. Fine Tuning
9.9. SIMILAR APPLICATIONS FOR ENGINEERS
9.10. EXERCISE PROBLEM
INDEX