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