Keras Deep Learning Online Course
Keras Deep Learning Online Course
The course begins with a foundation in Python basics, covering key concepts such as variables, control flow, lists, tuples, dictionaries, and functions. Following this, we introduce the Python NumPy library, designed to handle large arrays and matrices efficiently. A thorough theoretical session on deep learning sets the stage, explaining the core structure of an artificial neuron and its integration into an artificial neural network.
The course then moves into advanced topics, including convolutional neural networks (CNNs), text-based models, binary and multi-class classification, and image processing techniques. The journey concludes with a detailed study of Generative Adversarial Networks (GANs), progressing from foundational concepts to advanced applications.
Who is this course for?
This course is designed for newcomers aiming to excel in deep learning and Generative Adversarial Networks (GANs) starting from the basics. Progress from novice to advanced through immersive learning. Suitable for roles like machine learning engineer, deep learning specialist, AI researcher, data scientist, and GAN developer.
What you will learn
- Learn about Artificial Intelligence (AI) and machine learning
- Understand deep learning and neural networks
- Learn about lists, tuples, dictionaries, and functions in Python
- Learn Pandas, NumPy, and Matplotlib basics
- Explore the basic structure of artificial neurons and neural network
- Understand Stride, Padding, and Flattening concepts of CNNs
Course Outline
- Introduction
- Introduction to AI and Machine Learning
- Introduction to Deep learning and Neural Networks
- Setting Up Computer - Installing Anaconda
- Python Basics - Flow Control
- Python Basics - Lists and Tuples
- Python Basics - Dictionaries and Functions
- NumPy Basics
- Matplotlib Basics
- Pandas Basics
- Installing Deep Learning Libraries
- Basic Structure of Artificial Neuron and Neural Network
- Activation Functions Introduction
- Popular Types of Activation Functions
- Popular Types of Loss Functions
- Popular Optimizers
- Popular Neural Network Types
- King County House Sales Regression Model - Step 1 Fetch and Load Dataset
- Steps 2 and 3 - EDA and Data Preparation
- Step 4 - Defining the Keras Model
- Steps 5 and 6 - Compile and Fit Model
- Step 7 Visualize Training and Metrics
- Step 8 Prediction Using the Model
- Heart Disease Binary Classification Model - Introduction
- Step 1 - Fetch and Load Data
- Steps 2 and 3 - EDA and Data Preparation
- Step 4 - Defining the Model
- Step 5 – Compile, Fit, and Plot the Model
- Step 5 - Predicting Heart Disease Using Model
- Step 6 - Testing and Evaluating Heart Disease Model
- Redwine Quality Multiclass Classification Model - Introduction
- Step1 - Fetch and Load Data
- Step 2 - EDA and Data Visualization
- Step 3 - Defining the Model
- Step 4 – Compile, Fit, and Plot the Model
- Step 5 - Predicting Wine Quality Using Model
- Serialize and Save Trained Model for Later Usage
- Digital Image Basics
- Basic Image Processing Using Keras Functions
- Keras Single Image Augmentation
- Keras Directory Image Augmentation
- Keras Data Frame Augmentation
- CNN Basics
- Stride, Padding, and Flattening Concepts of CNN
- Flowers CNN Image Classification Model – Fetch, Load, and Prepare Data
- Flowers Classification CNN - Create Test and Train Folders
- Flowers Classification CNN - Defining the Model
- Flowers Classification CNN - Training and Visualization
- Flowers Classification CNN - Save Model for Later Use
- Flowers Classification CNN - Load Saved Model and Predict
- Flowers Classification CNN - Optimization Techniques - Introduction
- Flowers Classification CNN - Dropout Regularization
- Flowers Classification CNN - Padding and Filter Optimization
- Flowers Classification CNN - Augmentation Optimization
- Hyperparameter Tuning
- Transfer Learning Using Pre-Trained Models - VGG Introduction
- VGG16 and VGG19 Prediction
- ResNet50 Prediction
- VGG16 Transfer Learning Training Flowers Dataset
- VGG16 Transfer Learning Flower Prediction
- VGG16 Transfer Learning Using Google Colab GPU - Preparing and Uploading Dataset
- VGG16 Transfer Learning Using Google Colab GPU - Training and Prediction
- VGG19 Transfer Learning Using Google Colab GPU - Training and Prediction
- ResNet50 Transfer Learning Using Google Colab GPU - Training and Prediction
- Popular Neural Network Types
- Generative Adversarial Networks GAN Introduction
- Simple Transpose Convolution Using a Grayscale Image
- Generator and Discriminator Mechanism Explained
- A fully Connected Simple GAN Using MNIST Dataset - Introduction
- Fully Connected GAN - Loading the Dataset
- Fully Connected GAN - Defining the Generator Function
- Fully Connected GAN - Defining the Discriminator Function
- Fully Connected GAN - Combining Generator and Discriminator Models
- Fully Connected GAN - Compiling Discriminator and Combined GAN Models
- Fully Connected GAN - Discriminator Training
- Fully Connected GAN - Generator Training
- Fully Connected GAN - Saving Log at Each Interval
- Fully Connected GAN - Plot the Log at Intervals
- Fully Connected GAN - Display Generated Images
- Saving the Trained Generator for Later Use
- Generating Fake Images Using the Saved GAN Model
- Fully Connected GAN Versus Deep Convoluted GAN
- Deep Convolutional GAN - Loading the MNIST Handwritten Digits Dataset
- Deep Convolutional GAN - Defining the Generator Function
- Deep Convolutional GAN - Defining the Discriminator Function
- Deep Convolutional GAN - Combining and Compiling the Model
- Deep Convolutional GAN - Training the Model
- Deep Convolutional GAN - Training the Model Using Google Colab GPU
- Deep Convolutional GAN - Loading the Fashion MNIST Dataset
- Deep Convolutional GAN - Training the MNIST Fashion Model Using Google Colab GPU
- Deep Convolutional GAN - Loading the CIFAR-10 Dataset and Defining the Generator
- Deep Convolutional GAN - Defining the Discriminator
- Deep Convolutional GAN CIFAR-10 - Training the Model
- Deep Convolutional GAN - Training the CIFAR-10 Model Using Google Colab GPU
- Vanilla GAN Versus Conditional GAN
- Conditional GAN - Defining the Basic Generator Function
- Conditional GAN - Label Embedding for Generator
- Conditional GAN - Defining the Basic Discriminator Function
- Conditional GAN - Label Embedding for Discriminator
- Conditional GAN - Combining and Compiling the Model
- Conditional GAN - Training the Model
- Conditional GAN - Display Generated Images
- Conditional GAN - Training the MNIST Model Using Google Colab GPU
- Conditional GAN - Training the Fashion MNIST Model Using Google Colab GPU
- Other Popular GANs - Further Reference and Source Code Link
