Collectionless AI is the name we gave to a new perspective on AI/ML, focussed on “learning over time” in a continual manner, exploiting the information which is available at each time instant and interacting with other agents or humans. This setting has several important implications which might overcome the data-related issues which are typical of […]
Read More »KAMYAR ZEINALIPOUR When: Nov 15th, 2023 – 11:30 – 12:00 AM Where: Google meet link Description Applications of Large Language Models in the field of education This seminar explores the transformative impact of Large Language Models (LLMs) on education, focusing on their application in the generation of multilingual educational crosswords and quizzes. The seminar delves […]
Read More »Prof. Wolfang Utschick When: Apr 12th, 2023 – 10:00 – 13:00 AM Where: In presence at the San Niccolò building Bayesian Inference and Generative Models for Wireless Communication Algorithms Abstract: This tutorial first introduces the fundamentals of generative models, followed by the perspective of learning the radio propagation environment (“radio-compatible digital twin”) of wireless communication […]
Read More »VERONICA LACHI When: Apr 5th, 2023 – 11:00 – 11:30 AM Where: Google meet link Description The expressive power of pooling in Graph Neural Networks In Graph Neural Networks (GNNs), hierarchical pooling operators generate a coarser representation of the input data by creating local summaries of the graph structure and its vertex features. Considerable attention […]
Read More »GIUSEPPE ALESSIO D’INVERNO When: Mar 29th, 2023 – 15:00 – 15:30 AM Where: Google meet link Description Learning Identity Effects with Graph Neural Networks Graph Neural Networks (GNNs) have emerged in the past years as a powerful tool to learn tasks on a wide range of graph domains in a data-driven fashion; among all the […]
Read More »Caterina Graziani When: Mar 22th, 2023 – 11:00 – 11:30 AM Where: Google meet link Description RandomWalk Graph Neural Networks Abstract: In recent years, graph neural networks (GNNs) have become the de facto tool for performing machine learning tasks on graphs. Most GNNs belong to the family of message-passing neural networks (MPNNs). These models employ […]
Read More »Michele Casoni When: Mar 1th, 2023 – 11:00 – 11:30 AM Where: Google meet link Description Forward Approximate Solution for Linear Quadratic Tracking Abstract: “In this paper, we discuss an approximation strategy for solving the Linear Quadratic Tracking that is both forward and local in time. We exploit the known form of the value function […]
Read More »Marco Corneli When: Feb 22th, 2023 – 11:00 – 11:30 AM Where: Google meet link Description WebCrowDE – Template based Graph Neural Network with Optimal Transport Distances Abstract : Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing and aggregation with a specialized form of pooling. […]
Read More »Thomas Röthenbacher When: Feb 15th, 2023 – 11:30 – 12:00 AM Where: Google meet link Description WebCrowDE – Automated German Crossword resolution WebCrow is an automatic Crossword Puzzles solver for Italian and English. Adapting a crossword solver to other languages can be challenging because each language has its own characteristics and puzzles its own peculiarities. […]
Read More »BARBARA TONIELLA CORRADINI When: Feb 15th, 2023 – 11:00 – 11:30 AM Where: Google meet link Description Diffedit: Diffusion-based semantic image editing with mask guidance/strong> G. Couairon, J. Verbeek, H. Schwenk, and M. Cord Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text […]
Read More »