Description
Book SynopsisLearn, understand, and implement deep neural networks in a math- and programming-friendly approach using Keras and Python. The book focuses on an end-to-end approach to developing supervised learning algorithms in regression and classification with practical business-centric use-cases implemented in Keras.
The overall book comprises three sections with two chapters in each section. The first section prepares you with all the necessary basics to get started in deep learning. Chapter 1 introduces you to the world of deep learning and its difference from machine learning, the choices of frameworks for deep learning, and the Keras ecosystem. You will cover a real-life business problem that can be solved by supervised learning algorithms with deep neural networks. You''ll tackle one use case for regression and another for classification leveraging popular Kaggle datasets.
Later, you will see an interesting and challenging part of deep learning: hyperparameter tuning;
Table of Contents
SECTION 1: Prepares the reader with all the necessary gears to get started on the fast track ride in deep learning. Chapter 1: Deep Learning & Keras
Chapter Goal: Introduce the reader to the deep learning and keras framework
Sub -Topics
1. Exploring the popular Deep Learning frameworks
2. Overview of Keras, Pytorch, mxnet, Tensorflow,
3. A closer look at Keras: What’s special about Keras?
Chapter 2: Keras in Action
Chapter Goal: Help the reader to engage with hands-on exercises with Keras and implement the first basic deep neural network
Sub - Topics
1. A closer look at the deep learning building blocks
2. Exploring the keras building blocks for deep learning
3. Implementing a basic deep neural network with dummy data
SECTION 2 – Help the reader embrace the core fundamentals in simple lucid language while abstracting the math and the complexities of model training and validation with the least amount of code without compromising on flexibility, scale and the required sophistication
Chapter 3: Deep Neural networks for Supervised Learning
Chapter Goal: Embrace the core fundamentals of deep learning and its development
Sub - Topics:
1. Introduction to supervised learning
2. Classification use-case – implementing DNN
3. Regression use-case – implementing DNN
Chapter 4: Measuring Performance for DNN
Chapter Goal: Aid the reader in understanding the craft of validating deep neural networks
Sub - Topics:
1. Metrics for success – regression
2. Analyzing the regression neural network performance
3. Metrics for success – classification
4. Analyzing the regression neural network performance
SECTION 3 – Tuning and deploying robust DL models
Chapter 5: Hyperparameter Tuning & Model Deployment
Chapter Goal: Understand how to tune the model hyperparameters to achieve improved performance
Sub - Topics:
1. Hyperparameter tuning for deep learning models
2. Model deployment and transfer learning
Chapter 6: The Path Forward
Chapter goal – Educate the reader about additional reading for advanced topics within deep learning.
Sub - Topics:
1. What’s next for deep learning expertise?
2. Further reading
3. GPU for deep learning
4. Active research areas and breakthroughs in deep learning
5. Conclusion
