Program Overview

Research - An Introduction to Image Analysis with CNNs in Python

Overview

Convolutional Neural Networks (CNNs) are used in a wide variety of applications such as image classification, image segmentation, object detection, and image generation (with GAN). In this course, participants will learn how a CNN works and how it can be applied in practice in image classification and image segmentation by using Python programming.

Objectives

• Acquire the key competencies needed to use CNNs for image classification and image segmentation

Target Audience

• Any PhD students, post-docs, researchers of UNIL who would like to use CNNs in their research

Content

At the end of the course, participants are expected to:

• Understand how CNNs work
• Be able to use CNNs for image classification and image segmentation in Python

Length

• 1 day

Organization

• Once per year

Location

• In-person only (no online option)

Practicals

The practicals can be done on:

• The UNIL JupyterLab (available exclusively during this course and for one week following its completion)
• Participants' laptops (requiring installation of the necessary libraries)
• The UNIL cluster called Curnagl

Prerequisites

• Basic knowledge of deep learning: understanding how simple feedforward neural networks work, including interpreting accuracy and loss curves (for example, by attending the course "A Gentle Introduction to Deep Learning with Python and R")
• Comfort with Python programming

Additional Requirements for Practicals

• On UNIL JupyterLab: Access requires connection via the eduroam Wi-Fi with a UNIL account or through the UNIL VPN
• On participants' laptops: No account requirement
• On Curnagl: Registration using a UNIL email address
• Participants must bring their own laptops for the practical sessions