Interested in image processing? Then this course is for you!
This is currently the most comprehensive course in the market about convolutional neural networks. The course will guide you from zero to hero on a convolutional neural network which is mostly not covered in any other courses.
This course is built in a very practical way as there are lots of projects for you to practice along the way. So you will have lots of projects in your portfolio to show to your potential employers or clients
The course is split into 4 major parts:
Convolutional Neural Network fundamental
CIFAR-10 project
Clothing image project
Advanced implementation of CNN
PART 1: Convolutional Neural network fundamental
In this section, you will learn about the fundamental of the convolutional neural network. This is the first section so there will not be any advanced concept about CNN. This is just an introduction to what a convolutional neural network looks like, and what libraries we will be using. We will also implement a simple CNN model so you will learn how to build it with a detailed explanation step-by-step
PART 2: CIFAR-10 project
In this section, you will apply what will we have learned so far in the course to build a model for big dataset images. A convolution neural network is mostly used for image processing. This project will help us to reinforce what we have learned so far in the course. Furthermore, it will help us to combine the knowledge together to build a model for the big dataset.
PART 3: Clothing image project
This is another project for you to practice. Similar to the CIFAR-10 project, this project will have you hands-on practice with detailed explanations step-by-step.
PART 4: Advanced implementation of CNN.
In this section, we will learn some of the advanced tools and libraries in CNN which are not covered in any other courses. VGG, Inception network and the deep dream network will be introduced in this section. We will also implement VGG, Inception network, and the deep dream network in the project "combining two images". Furthermore we will also learn how to improve the result in this section.
