[Jun 16th 2021] LabMeeting: Advanced ML methods to understand the genetic mechanism of COVID-19 severity and multi-organ involvement

Marco Tanfoni (University of Siena) When: Jun 16th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description The main goal of this study was to establish a link between COVID-19 lung damage and existing mutations on some genes, particularly with regard to disease severity. A regularized logistic regression model was implemented to identify […]

Read More »

Language Models for Text Understanding and Generation

Author: Andrea Zugarini Date: May, 2021 Topics: Language Modeling; Language Generation; Language Understanding; Information Extraction. Abstract The ability to understand and generate language is one of the most fascinating and peculiar aspects of humankind. We can discuss with other individuals about facts, events, stories or the most abstract aspects of our existences, only because of […]

Read More »

[May 19th 2021] LabMeeting: Friendly Training

Simone Marullo (University of Siena) When: May 19, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Two papers by Simone Marullo, Matteo Tiezzi, Marco Gori and Stefano Melacci will be presented: – Friendly Training: Neural Networks Can Adapt Data To Make Learning Easier – Being Friends Instead of Adversaries: Deep Networks Learn […]

Read More »

[May 12th 2021] LabMeeting: Graph Dynamic Embedding

Veronica Lachi (University of Siena) When: May 12, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Representation learning of static and more recently dynamically evolving graphs has gained noticeable attention. Existing approaches for modelling graph dynamics focus extensively on the evolution of individual nodes independently of the evolution of mesoscale community structures. […]

Read More »

[Apr 21st 2021] LabMeeting: A Representer Theorem for Deep Neural Networks

Giuseppe Alessio D’Inverno (University of Siena) When: Apr 21, 2021 – 11:00 – 11:45 AM Where: Google meet link Description We propose to optimize the activation functions of a deep neural network by adding a corresponding functional regularization to the cost function. We justify the use of a second- order total-variation criterion. This allows us […]

Read More »

Local Propagation in Neural Network Learning by Architectural Constraints

Author: Matteo Tiezzi Date: March, 2021 Topics: Learning by Constraints; Constraint optimization; Graph Neural Networks; Lifelong Learning. Abstract A crucial role for the success of the Artificial Neural Networks (ANN) processing scheme has been played by the feed-forward propagation of signals. The input patterns undergo a series of stacked parametrized transformations, which foster deep feature […]

Read More »

TAILOR Task 4.3 Workshop

Workshop on “Learning and Reasoning with Embeddings, Knowledge Graphs & Ontologies” First Workshop for Task 4.3 of  TAILOR project With the partecipation of Task 7.4 of AI4EU project June 8, 2021 – 09:30-13:00 Google Meet Conference Room: https://meet.google.com/ewq-zxpx-sub   Abstract Integrating Learning and Reasoning is a fundamental problem in AI, especially in application domains dealing with relational […]

Read More »

[Apr 14th 2021] LabMeeting: Incorporating network based protein complex discovery into automated model construction

Federica Baccini (University of Siena) When: Apr 14, 2021 – 11:00 – 11:45 AM Where: Google meet link Description We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs. The structural construction of the computational graphs is driven by the use of topological […]

Read More »