Deep Learning and Computer Vision

Deep Learning is a branch of Machine Learning that has recently achieved impressive results in several different domains. Computer Vision is unquestionably one of the fields where Deep Learning shows the most astonishing performance in the real world. This school, composed of two crash courses in synergy, will cover basic principles of deep architectures, with a focus on visual data. At the same time, it will provide a complementary introduction to basic principles of computer vision and visual perception in artificial agents.

A guided tour on recent deep learning approaches for computer vision tasks will also be provided. Besides the analysis of well-established approaches, the course will highlight current trends, open problems, and potential future lines of research.

The theoretical classes will be coupled with hands-on activities in Python using Keras and OpenCV libraries. Starting from the basics of neural networks and computer vision, we will dive into more complex approaches, currently at the state-of-the-art. The last day of the school will be focused on a project developed in groups, which will be the basis of the final evaluation. Still, all participants are welcome to attend as this activity is a part of the educational objectives of the school.

During this intense week, a poster session and aperitif will be organized, an occasion for an informal discussion about your current and future research! Although DLCV is conceived as a school, the two courses can also be taken independently.

Fundamentals of Machine Learning