[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 WP4.3 Workshop

Workshop on “Learning and Reasoning with Embeddings, Knowledge Graphs & Ontologies” WP4 of TAILOR project –¬†Task 4.3 Expected date – June 8, 2021 Conference Room:¬†Google Meet   Abstract Integrating Learning and Reasoning is a fundamental problem in AI, especially in application domains dealing with relational data, such as knowledge graphs and ontologies. During this workshop, […]

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 »