Preface
Acknowledgments
Introduction: Python and Array Operations
Introduction
Anaconda Installation
Using Jupyter Notebook
Array Computing Using NumPy
Importing NumPy and Basic Commands
Changing Array Elements
Creating Array with Specific Values
Broadcasting in NumPy
Introduction to PyTorch
Introduction
Setting up PyTorch
Basic PyTorch Operations
Basic Artificial Neural Network and Architectures
Introduction
Applications
Neurons and Activation Functions
Sigmoid Activation
Hyperbolic Tangent Activation
Rectified Linear Units (ReLU) Activation
Leaky Rectified Linear Units (Leaky ReLU) Activation
Exponential Linear Units (ELU) Activation
SoftPlus Activation
Minimizing the Loss Function
Gradient Descent Algorithm
Introduction to Deep Learning
Introduction
Convolutional Neural Network
Pooling Layer
Fully Connected Layer
Recurrent Neural Network (RNN)
Basic Structures
Other Deep Learning Models
Deep Transfer Learning
Introduction
Types of Transfer Learning
Using Pre-Trained Networks
Feature Extraction, Fine Tuning, and Data Augmentation
Model Evaluation
Setting Up PyTorch and Google Cloud Platform Console
Introduction
Setting Up a GCP Account
Create a New Project
Set Up a VM instance
GPU Quota Request
A Cost-Effective Approach
VPC Network
Set Up External IP Address
Create Firewall Rules
Setting Up VM Instance to Run Models
Anaconda Installation on VM
Jupyter Notebook Set Up
Case Study: Practical Implementation Through Transfer Learning
Problem Statement
Data Processing
Upload Data into Storage Bucket
Transferring File to VM Instance
Transfer Learning Steps
Define Loss Function and Optimizer
Install Dependencies
Import Libraries
Checkpoint and Adaptive Learning Rate
Set Seed
Dataset Class and Augmentation
Data Preprocessing
Transfer Learning Model (EfficientNet-B7)
Fine-Tuning and Training
Model Testing
Conclusion
Bibliography
Author's Biography
Blank Page