Deep Learning Using Keras - A Complete and Compact Guide for Beginners

Deep Learning Using Keras - A Complete and Compact Guide for Beginners

by Abhilash Nelson
Released October 2021
Publisher(s): Packt Publishing
ISBN: 9781803242835

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

The artificial intelligence domain is divided broadly into deep learning and machine learning. In fact, deep learning is machine learning itself but deep learning with its deep neural networks and algorithms tries to learn high-level features from data without human intervention. That makes deep learning the base of all future self-intelligent systems.

This course begins with going over the basics of Python and then quickly moves on to important libraries of Python that are critical to data analysis and visualizations, such as NumPy, Pandas, and Matplotlib. After the basics, we will then install the deep learning libraries—Theano and TensorFlow—and the API for dealing with these called Keras.

Then, before we jump into deep learning, we will have an elaborate theory session about the basic structure of artificial neuron and neural networks, and about activation functions, loss functions, and optimizers.

Furthermore, we will create deep learning multi-layer neural network models for a text-based dataset and then convolutional neural networks for an image-based dataset.

You will also learn how the basic CNN layers such as the convolution layer, the pooling layer, and the fully connected layer work. Then, we will use different techniques to improve the quality of a model and perform optimization using image augmentation.

By the end of this course, you will have a complete understanding of deep learning and will be able to implement these skills in your own projects.

What You Will Learn

  • Learn the basics of Python programming
  • Use different Python libraries such as NumPy, Matplotlib, and Pandas
  • Understand the basic structure of artificial neurons and neural networks
  • Explore activation functions, loss functions, and optimizers
  • Create deep learning multi-layer neural network models for a text-based dataset
  • Create convolutional neural networks for an image-based dataset

Audience

This course is designed for beginners who want to learn basic to advanced deep learning and have basic computer knowledge.

About The Author

Abhilash Nelson: Abhilash Nelson is a pioneering, talented, and security-oriented Android/iOS mobile and PHP/Python web application developer with more than 8 years of IT experience involving designing, implementing, integrating, testing, and supporting impactful web and mobile applications. He has a master's degree in computer science and engineering and has PHP/Python programming experience, which is an added advantage for server-based Android and iOS client applications. Abhilash is currently a senior solution architect managing projects from start to finish to ensure high quality and innovative and functional design.

Table of contents

  1. Chapter 1 : Course Introduction
    1. Course Introduction and Table of Contents
  2. Chapter 2 : Introduction
    1. Introduction to AI (Artificial Intelligence) and Machine Learning
    2. Introduction to Deep learning
  3. Chapter 3 : Setting Up Computer
    1. Installing Anaconda
  4. Chapter 4 : Python Basics
    1. Assignment
    2. Flow Control - Part 1
    3. Flow Control - Part 2
    4. List and Tuples
    5. Dictionary and Functions - part 1
    6. Dictionary and Functions - part 2
  5. Chapter 5 : NumPy Basics
    1. NumPy Basics - Part 1
    2. NumPy Basics - Part 2
  6. Chapter 6 : Matplotlib Basics
    1. Matplotlib Basics - part 1
    2. Matplotlib Basics - part 2
  7. Chapter 7 : Pandas Basics
    1. Pandas Basics - Part 1
    2. Pandas Basics - Part 2
  8. Chapter 8 : Installing Libraries
    1. Installing Deep Learning Libraries
  9. Chapter 9 : Artificial Neuron and Neural Network
    1. Basic Structure
  10. Chapter 10 : Activation Functions
    1. Introduction
  11. Chapter 11 : Popular Activation Functions
    1. Popular Types of Activation Functions
  12. Chapter 12 : Popular Types of Loss Functions
    1. Popular Types of Loss Functions
  13. Chapter 13 : Popular Types of Optimizers
    1. Popular Optimizers
  14. Chapter 14 : Popular Neural Network Types
    1. Popular Neural Network Types
  15. Chapter 15 : King County House Sales Regression Model
    1. Step 1 - Fetch and Load Dataset
    2. Step 2 and 3 - EDA (Exploratory Data Analysis) and Data Preparation - Part 1
    3. Step 2 and 3 - EDA and Data Preparation - Part 2
    4. Step 4 - Defining the Keras Model - Part 1
    5. Step 4 - Defining the Keras Model - Part 2
    6. Step 5 and 6 - Compile and Fit Model
    7. Step 7 - Visualize Training and Metrics
    8. Step 8 - Prediction Using the Model
  16. Chapter 16 : Heart Disease Binary Classification Model
    1. Heart Disease Binary Classification Model - Introduction
    2. Step 1 - Fetch and Load Data
    3. Step 2 and 3 - EDA and Data Preparation - Part 1
    4. Step 2 and 3 - EDA and Data Preparation - Part 2
    5. Step 4 - Defining the Model
    6. Step 5 and 6 - Compile Fit and Plot the Model
    7. Step 7 - Predicting Heart Disease Using Model
  17. Chapter 17 : Red Wine Quality Multiclass Classification Model
    1. Introduction
    2. Step 1 - Fetch and Load Data
    3. Step 2 and 3 - EDA and Data Visualization
    4. Step 4 - Defining the Model
    5. Step 5 and 6 - Compile Fit and Plot the Model
    6. Step 7 - Predicting Wine Quality using Model
    7. Serialize and Save Trained Model for Later Use
  18. Chapter 18 : Digital Image Basics
    1. Digital Image
    2. Basic Image Processing Using Keras Functions - Part 1
    3. Basic Image Processing Using Keras Functions - Part 2
    4. Basic Image Processing Using Keras Functions - Part 3
  19. Chapter 19 : Image Augmentation
    1. Keras Single Image Augmentation - Part 1
    2. Keras Single Image Augmentation - Part 2
    3. Keras Directory Image Augmentation
    4. Keras Data Frame Augmentation
  20. Chapter 20 : Convolutional Neural Network
    1. CNN (Convolutional Neural Networks) Basics
    2. Stride Padding and Flattening Concepts of CNN
  21. Chapter 21 : Flowers CNN Image Classification Model
    1. Fetch Load and Prepare Data
    2. Create Test and Train Folders
    3. Defining the Model - Part 1
    4. Defining the Model - Part 2
    5. Defining the Model - Part 3
    6. Training and Visualization
    7. Save Model for Later Use
    8. Load Saved Model and Predict
    9. Improving Model - Optimization Techniques
    10. Dropout Regularization
    11. Padding and Filter Optimization
    12. Augmentation Optimization
    13. Hyper Parameter Tuning - Part 1
    14. Hyper Parameter Tuning - Part 2
  22. Chapter 22 : Transfer Learning Using Pretrained Models
    1. VGG Introduction
  23. Chapter 23 : VGG16 and VGG19 Prediction
    1. VGG16 and VGG19 Prediction - Part 1
    2. VGG16 and VGG19 Prediction - Part 2
  24. Chapter 24 : ResNet50
    1. ResNet50 Prediction
  25. Chapter 25 : Transfer Learning Training Flowers Dataset
    1. VGG16 - Part 1
    2. VGG16 - Part 2
  26. Chapter 26 : Transfer Learning Flower Prediction
    1. VGG16 Transfer Learning Flower Prediction
  27. Chapter 27 : VGG16 Transfer Learning Using Google Colab GPU
    1. Preparing and Uploading Dataset
    2. Training and Prediction
  28. Chapter 28 : VGG19 Transfer Learning using Google Colab GPU
    1. Training and Prediction
  29. Chapter 29 : ResNet-50 Transfer Learning using Google Colab GPU
    1. Training and Prediction

Product information

  • Title: Deep Learning Using Keras - A Complete and Compact Guide for Beginners
  • Author(s): Abhilash Nelson
  • Release date: October 2021
  • Publisher(s): Packt Publishing
  • ISBN: 9781803242835