- You will learn how to build convolutional neural networks (CNNs) to classify landmark images based on patterns and objects that appear in them;
- Build models to automatically predict the location of an image based on any landmarks depicted in the image;
- Go through the machine learning design process end-to-end - performing data preprocessing, designing and training CNNs, comparing the accuracy of different CNNs, and deploying an app based on the best CNN learners had trained.
- You will learn the main characteristics of CNN that make them better than standard neural networks for image processing.
- You’ll also examine the inner workings of CNNs and apply the architectures to custom datasets using transfer learning.
- Finally, you will learn how to use CNNs for object detection and semantic segmentation.
You need to be familiar with the following for the course:
- Experience with Python programming language
- Understanding of Deep Learning (Gradient decent, activation function, etc)
- Knowledge of Linear Algebra, Derivatives, Numpy, Jupyter notebooks, etc.
This is a 100% e-learning, self-paced and self-directed course that runs on a PC/Laptop's web browser.
Depending on your experience and prior knowledge, you may spend up to 15 hours per week to finish this 1-month course.
Certification
Learners will be awarded the Advanced Course certification on passing a project within the 1-month course duration.