Autoencoders

4 hours of instruction

This course takes students through a journey into the world od autoencoders – a set of powerful deep learning models that have a special place in the world of image analysis. By the end of this course students will be able to navigate through the application space of autoencoders and implement autoencoders to perform tasks such as image denoising and more.

OBJECTIVES

1. Define use cases for autoencoders and what tasks they can do in the image analysis space
2. Implement convolutional and denoising autoencoders

PREREQUISITES

Convolutional Neural Networks (CNN) for Image Recognition

SYLLABUS & TOPICS COVERED

1. Autoencoder Overview
   • Autoencoders and their use cases in image processing
   • Architecture of a simple autoencoder
2. Autoencoder Implementation
   • Implementation of convolutional
   • Implementation of denoising autoencoder

SOFTWARE REQUIREMENTS

You will have access to a Python-based JupyterHub environment for this course. No additional download or installation is required.