Resource Registry: Deep learning

The Computational Intelligence Research Group (CIRG) focuses on various aspects of fundamental and applied computational intelligence and machine learning research. Nature-inspired algorithms such as artificial neural networks, deep learning methods, self-organizing maps, particle swarm optimization and evolutionary computing are studied both theoretically and practically. Real-life applications include computer vision, data mining and anomaly detection.

This Short Learning Program is focused on the creation of intelligent systems using a multitude of modern techniques and technologies. This programme balances the practical implementation of such systems with a solid grounding in the fundamentals so that you will be have a deeper knowledge of the deepest learning techniques.

Galaxy morphology characterisation is an important area of study, as the type and formation of galaxies offer insights into the origin and evolution of the universe. Owing to the increased availability of images and galaxies, scientists have turned crowd-sourcing to automate the process of instance labelling. However, research has shown that using crowd-sourced labels for galaxy classification comes with many pitfalls. An alternative approach to galaxy classification is metric learning. Metric learning allows for improved representations for classification, anomaly detection, information retrieval, clustering and dimensionality reduction. Understanding the implications of this approach regarding crowd-sourced labels is of paramount importance if scientists intend to continue using them.