An Open Class is to be held at 06:30 PM on monday 28-06-2021 on Postgraduate in Artificial Intelligence with Deep Learning (Face-to-face) and Postgraduate in Artificial Intelligence with Deep Learning (Online).
Deep learning has achieved remarkable results in fields such as computer vision, speech recognition and natural language processing.
In this session, Dr McGuinness will explain how to develop visual search engines based on deep learning. The first generation of deep image retrieval systems used off-the-shelf features developed for other tasks, but soon the technology advanced to actually train neural networks tailored for assessing the similarity between a query image and those stored in a large dataset. The class will also cover retrieval-specific techniques such as reranking or query expansion, which can be extrapolated to any domain beyond computer vision. The session will include hands-on examples in PyTorch, available to all attendees through a Google Colab notebook on the cloud.
The speaker
Dr Kevin McGuinness is an Assistant Professor with the School of Electronic Engineering in Dublin City University and a Science Foundation Ireland Funded Investigator at the Insight SFI Centre for Data Analytics and in the ENABLE research programme. He finished my B.Sc (Hons) in Computer Applications and Software Engineering in Dublin City University in 2005 and was awarded a Ph.D. from the School of Electronic Engineering in 2009. He has since been a postdoctoral researcher at the CLARITY Centre for Sensor Web Technologies, and a research fellow at the Insight SFI Centre for Data Analytics. His primary research interests are computer vision, deep learning, image and video segmentation, segmentation evaluation, machine learning, content-based multimedia information retrieval, and human-computer interaction.
Dr McGuinness was one of the pioneers in the introduction of deep learning at UPC, where he has been teaching since 2015, first at the ETSETB TelecomBCN School, and now UPC School.
The session will take place on-line using Google Meet.
As well, you can follow the Open Class using your mobile device by downloading the corresponding Google Meet application for your Android or iOS.
This event is open and free. To attend, please confirm using the "I Will attend". Limited places.