Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch

Table of Contents
About the Authors
About the Technical Reviewers
Acknowledgments
Introduction
Chapter 1: Introduction to Machine Learning and Deep Learning
	Defining Deep Learning
		A Brief History
			Rule-Based Systems
			Knowledge-Based Systems
			Machine Learning
			Deep Learning
	Advances in Related Fields
	Prerequisites
	The Approach Ahead
	Installing the Required Libraries
	The Concept of Machine Learning
	Binary Classification
	Regression
	Generalization
	Regularization
	Summary
Chapter 2: Introduction to PyTorch
	Why Do We Need a Deep Learning Framework?
	What Is PyTorch?
	Why PyTorch?
	It All Starts with a Tensor
	Creating Tensors
	Tensor Munging Operations
	Mathematical Operations
	Element-Wise Mathematical Operations
	Trigonometric Operations in Tensors
	Comparison Operations for Tensors
	Linear Algebraic Operations
	Summary
Chapter 3: Feed-Forward Neural Networks
	What Is a Neural Network?
		Unit
		The Overall Structure of a Neural Network
		Expressing a Neural Network in Vector Form
		Evaluating the Output of a Neural Network
		Training a Neural Network
	Deriving Cost Functions Using Maximum Likelihood
		Binary Cross-Entropy
		Cross-Entropy
		Squared Error
		Summary of Loss Functions
	Types of Activation Functions
		Linear Unit
		Sigmoid Activation
		Softmax Activation
		Rectified Linear Unit
		Hyperbolic Tangent
	Backpropagation
		Gradient Descent Variants
			Batch Gradient Descent
			Stochastic Gradient Descent
			Mini-Batch Gradient Descent
		Gradient-Based Optimization Techniques
			Gradient Descent with Momentum
			RMSprop
			Adam
	Practical Implementation with PyTorch
	Summary
Chapter 4: Automatic Differentiation in Deep Learning
	Numerical Differentiation
	Symbolic Differentiation
	Automatic Differentiation Fundamentals
		Implementing Automatic Differentiation
			What Is Autograd?
	Summary
Chapter 5: Training Deep Leaning Models
	Performance Metrics
		Classification Metrics
		Regression Metrics
			Mean Squared Error
			Mean Absolute Error
			Mean Absolute Percentage Error
	Data Procurement
	Splitting Data for Training, Validation, and Testing
	Establishing the Achievable Limit on the Error Rate
	Establishing the Baseline with Standard Choices
	Building an Automated, End-to-End Pipeline
		Orchestration for Visibility
	Analysis of Overfitting and Underfitting
	Hyperparameter Tuning
	Model Capacity
	Regularizing the Model
	Early Stopping
	Norm Penalties
	Dropout
	A Practical Implementation in PyTorch
		Interpreting the Business Outcomes for Deep Learning
	Summary
Chapter 6: Convolutional Neural Networks
	Convolution Operation
	Pooling Operation
	Convolution-Detector-Pooling Building Block
		Stride
		Padding
		Batch Normalization
		Filter
		Filter Depth
		Number of Filters
	Summarizing key learnings from CNNs
		Implementing a basic CNN using PyTorch
		Implementing a larger CNN in PyTorch
		CNN Thumb Rules
	Summary
Chapter 7: Recurrent Neural Networks
	Introduction to RNNs
	Training RNNs
	Bidirectional RNNs
	Vanishing and Exploding Gradients
	Gradient Clipping
	Long Short-Term Memory
	Practical Implementation
	Summary
Chapter 8: Recent Advances in Deep Learning
	Going Beyond Classification in Computer Vision
		Object Detection
		Image Segmentation
		Pose Estimation
		Generative Computer Vision
	Natural Language Processing with Deep Learning
		Transformer Models
		Bidirectional Encoder Representations from Transformers
	GrokNet
	Additional Noteworthy Research
	Concluding Thoughts
Index