Deep Learning Using Keras Online Course

Deep Learning Using Keras Online Course

This course provides a complete introduction to deep learning, starting with Python basics and essential libraries like NumPy, Pandas, and Matplotlib before moving on to frameworks such as TensorFlow, Theano, and Keras. You’ll learn the theory behind neural networks, including activation functions, loss functions, and optimizers, and then apply this knowledge to build multi-layer models for text data and convolutional neural networks (CNNs) for image data. With hands-on practice in CNN layers, model optimization, and techniques like image augmentation, you’ll gain the skills to confidently implement deep learning in real-world projects.

Who should take this Course?

The Deep Learning CNN with Python Online Course is designed for data scientists, AI/ML practitioners, software developers, and researchers who want to gain practical expertise in convolutional neural networks for computer vision and image processing. It is also valuable for students and professionals in fields such as robotics, healthcare, and automation who are looking to apply Python-based CNNs to real-world projects and innovations.

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

Course Outline

Course Introduction

• Course Introduction and Table of Contents

Introduction

• Introduction to AI (Artificial Intelligence) and Machine Learning
• Introduction to Deep learning

Setting Up Computer

• Installing Anaconda

Python Basics

• Assignment
• Flow Control - Part 1
• Flow Control - Part 2
• List and Tuples
• Dictionary and Functions - part 1
• Dictionary and Functions - part 2

NumPy Basics

• NumPy Basics - Part 1
• NumPy Basics - Part 2

Matplotlib Basics

• Matplotlib Basics - part 1
• Matplotlib Basics - part 2

Pandas Basics

• Pandas Basics - Part 1
• Pandas Basics - Part 2

Installing Libraries

• Installing Deep Learning Libraries

Artificial Neuron and Neural Network

• Basic Structure

Activation Functions

• Introduction

Popular Activation Functions

• Popular Types of Activation Functions

Popular Types of Loss Functions

• Popular Types of Loss Functions

Popular Types of Optimizers

• Popular Optimizers

Popular Neural Network Types

• Popular Neural Network Types

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

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

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

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

Image Augmentation

• Keras Single Image Augmentation - Part 1
• Keras Single Image Augmentation - Part 2
• Keras Directory Image Augmentation
• Keras Data Frame Augmentation

Convolutional Neural Network

• CNN (Convolutional Neural Networks) Basics
• Stride Padding and Flattening Concepts of CNN

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
• Transfer Learning Using Pretrained Models

VGG Introduction

• VGG16 and VGG19 Prediction
• VGG16 and VGG19 Prediction - Part 1
• VGG16 and VGG19 Prediction - Part 2

ResNet50

• ResNet50 Prediction

Transfer Learning Training Flowers Dataset

• VGG16 - Part 1
• VGG16 - Part 2

Transfer Learning Flower Prediction

• VGG16 Transfer Learning Flower Prediction
• VGG16 Transfer Learning Using Google Colab GPU

Preparing and Uploading Dataset

• Training and Prediction

VGG19 Transfer Learning using Google Colab GPU

• Training and Prediction
• ResNet-50 Transfer Learning using Google Colab GPU
• Training and Prediction