Extremely happy and excited to share that our paper “Graph Mixture Density Networks” has been accepted for publication at ICML 2021! Huge congrats to Federico Errica for his second ICML paper and to Alessio Micheli who shares with me Federico’s supervision towards a brilliant Ph.D!

Check out the paper (soon on Arxiv in camera-ready form) to discover how we introduced first model for learning multi-modal output distributions conditioned on arbitrary graphs, and its application to epidemiology.

Another big graduation day today, with plenty of contributions from our group! Congratulations to all students for their achievement. Check them out below. Pleanty of cool stuff including distillation-based continual learning, medical image analysis and generation, reinforcement learning and quantum computing as well as emotion understanding. Well done to all of you!

Apprendimento con rinforzo: un’esperienza d’uso nel gioco Asso Pigliatutto, Enrico Tomasi, Laurea in Informatica, Università di Pisa, A.A. 2019/2020

Distilled Replay: Mitigating Forgetting through Dataset Distillation (co-supervised with A. Carta, A. Cossu), Andrea Rosasco, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

ANSIA: A Neural System that Infers Affects (co-supervised with C.Gallicchio), Matteo Montalbetti, Laurea in Informatica, Università di Pisa, A.A. 2019/2020

Quantum Control via Deep Reinforcement Learning using IBMQ platform and Qiskit Pulse (co-supervision by Enrico Prati, CNR), Rudy Semola, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Tomography reconstruction with end-to-end neural networks, Matteo Ronchetti, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Dynamic neural networks for COVID-19 severity prediction from lung ultrasound (co-supervised with F. Faita, IFC-CNR), Ruggiero Santo, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Big graduation day in the ML family with 3 newly graduated students (two cum laude!) on topics ranging from neuro-probabilistic models for graphs, interpretability of graph neural networks for chemistry and cognitive architectures for creativity. Congratulations!

Daniele Arioli, CognAC: a cognitive architecture based on Information Dynamics of Thinking, co-supervised with V. Gervasi, M.Sc. in Computer Science & Artificial Intelligence

Valerio De Caro, Graph Relative Density Networks, M.Sc. in Computer Science & Artificial Intelligence

Danilo Numeroso, Explaining Deep Graph Networks By Structured Counterfactual Explanations, M.Sc. in Computer Science & Artificial Intelligence

Congratulations (with some delay) to my students who graduated with two theses on the LISTIT project.

Valerio De Caro extended the Hidden Markov Tree Network and developed an efficient implementation of the model.

Michele Colombo developed a Conditional Variational Autoencoder for learning tree to tree  transductions with application to machine translation.

Just finished presenting our new paper @ESANN2016

Check-it out at ESANN website as it will soon be out in free electonic version.