prof. Davide Bacciu
1 - Deep learning primer - Applications, challenges, and research directions
The seminar will take the audience on a shortcut across decades of Artificial Neural Network research, introducing the key concepts and ideas underlying computational neural models and surveying the most recent developments of the field falling under the “Deep Learning” umbrella term. We will discuss impactful applications of deep neural networks covering several domains, ranging from computer science, to engineering, medicine, biology, and physics. The seminar will conclude with a selection of open research challenges in the field.
2 - Deep graph networks – Learning from data, relationships, and prior knowledge
The seminar will provide an easy paced introduction to the lively field of deep learning for graphs, its applications, and open challenges. Graphs are an effective representation for complex information, providing a straightforward means to bridge numerical data and symbolic relationships. Dealing with graph data requires learning models capable of adapting to structured samples of varying size and topology, capturing the relevant structural patterns to perform predictive and explorative tasks while maintaining the efficiency and scalability necessary to process large scale networks. We will discuss the most recent advancements in terms of deep graph networks and survey relevant applications including drug repurposing, prediction of chemo-physical properties of compounds, molecule generation, social network analysis, recommendation systems and others.