the APPLIED TENSORFLOW AND KERAS WORKSHOP - build your practical skills by working through a real... -world project - a bitcoin price prediction tracke.

Cover
FM
Copyright
Table of Contents
Preface
Chapter 1: Introduction to Neural Networks and Deep Learning
	Introduction
	What are Neural Networks?
		Successful Applications of Neural Networks
	Why Do Neural Networks Work So Well?
		Representation Learning
		Function Approximation
		Limitations of Deep Learning
		Inherent Bias and Ethical Considerations
		Common Components and Operations of Neural Networks
	Configuring a Deep Learning Environment
		Software Components for Deep Learning
			Python 3
			TensorFlow
			Keras
			TensorBoard
			Jupyter Notebook, Pandas, and NumPy
		Exercise 1.01: Verifying the Software Components
	Exploring a Trained Neural Network
		The MNIST Dataset
		Training a Neural Network with TensorFlow
		Exercise 1.02: Training a Neural Network Using the MNIST Dataset
		Testing Network Performance with Unseen Data
		Activity 1.01: Training a Neural Network with Different Hyperparameters
	Summary
Chapter 2: Real-World Deep Learning: Predicting the Price of Bitcoin
	Introduction
	Choosing the Right Model Architecture
		Convolutional Neural Networks (CNNs)
		Recurrent Neural Networks (RNNs)
		Long Short-Term Memory (LSTM) Networks
		Generative Adversarial Networks
		Deep Reinforcement Learning (DRL)
		Data Normalization
			Z-Score
			Point-Relative Normalization
			Maximum and Minimum Normalization
	Structuring Your Problem
		Jupyter Notebook
		Exercise 2.01: Exploring the Bitcoin Dataset and Preparing Data for a Model
	Using Keras as a TensorFlow Interface
		Model Components
		Exercise 2.02: Creating a TensorFlow Model Using Keras
	From Data Preparation to Modeling
		Training a Neural Network
		Reshaping Time Series Data
		Making Predictions
			Overfitting
		Activity 2.01: Assembling a Deep Learning System
	Summary
Chapter 3: Real-World Deep Learning: Evaluating the Bitcoin Model
	Introduction
		Problem Categories
		Loss Functions, Accuracy, and Error Rates
		Different Loss Functions, Same Architecture
		Using TensorBoard
		Implementing Model Evaluation Metrics
		Evaluating the Bitcoin Model
		Overfitting
		Model Predictions
		Interpreting Predictions
		Exercise 3.01: Creating an Active Training Environment
	Hyperparameter Optimization
		Layers and Nodes – Adding More Layers
			Adding More Nodes
		Layers and Nodes – Implementation
		Epochs
			Epochs – Implementation
		Activation Functions
		Linear (Identity) Functions
			Hyperbolic Tangent (Tanh) Function
			Rectified Linear Unit Functions
		Activation Functions – Implementation
		Regularization Strategies
			L2 Regularization
			Dropout
			Regularization Strategies – Implementation
		Optimization Results
		Activity 3.01: Optimizing a Deep Learning Model
	Summary
Chapter 4: Productization
	Introduction
	Handling New Data
		Separating Data and Model
		The Data Component
		The Model Component
		Dealing with New Data
			Retraining an Old Model
			Training a New Model
		Exercise 4.01: Retraining a Model Dynamically
		Deploying a Model as a Web Application
		Application Architecture and Technologies
		Exercise 4.02: Deploying and Using Cryptonic
		Activity 4.01: Deploying a Deep Learning Application
	Summary
Appendix
Index