The course provides an introduction to deep learning and specifically to deep learning for visual computing. Example topics that will be discussed are: simple fully connected neural networks, image classification, convolutional neural networks, backpropagation, activation functions, data normalization, data augmentation, normalization layers, training dynamics, network architectures, style transfer, segmentation, object detection, regression, optimization, autoencoder, generative adversarial networks, networks for point cloud processing, clustering, recursive neural networks, graphconvolutional neural networks, adversarial attacks. The course starts at a very basic level. However, previous skills especially programming in Python, Machine Learning, Linear Algebra, Probability, and multi-variate Calculus will be required. Students are expected to learn these skills quickly if they did not have sufficient exposure to them. The evaluation will heavily rely on projects. Therefore programming skills are the most important.

This course provides an overview of deep learning applications in visual computing. We will cover some basics of deep learning (optimization, network architecture, compression, …) as well as selected applications (image recognition, segmentation, image synthesis, object detection, object synthesis, mesh segmentation, point cloud processing, …). The selection of the applications is expected to change with different course offerings and will be adapted to the latest research papers in computer vision and computer graphics.

Bronze Medal