A paper on a deep concentric reservoir architecture has just been accepted for IJCNN 2018! Congratulations to my student Andrea Bongiorno for his first work!
Now available on Arxiv!
Big day for a hoard of my students graduating today with ML theses!
Antonio Bruno developed a deep learning model for learning tree transductions in the LISTIT project.
Andrea Bongiorno proposes a new deep architecture for reservoirs based on concentric topologies.
Federico Errica discussed (cum Laude!) a new deep generative model for contextual processing of graphs.
Alessio Gravina studied how to help clinicians in early prediction of BPD in low birth-weight infants.
Many congrats as well to Ahmed Alleboudy and Ruben Matino whom I followed in their external theses as UNIPI supervisor.
Check out this opportunity of meeting and discussing with world leaders in AI at ACDL 2018, Certosa di Pontignano, Siena, July 19-23 2018.
The course will feature lectures from Yoshua Bengio, Yann Lecun, Marco Gori, Peter Norvig, Alex Pentland and many others.
First congratulations to my student Daniele for his first scientific paper:
Mixture of Hidden Markov Models as Tree Encoder. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'18), i6doc.com, Louvain-la-Neuve, Belgium, 2018, ISBN: 978-287587047-6.
Great success also for the Deep Learning in Bionformatics special session I am co-organizing. We received an high number of great quality papers but only 20% had to be chosen for the oral plenary. Check out the program here!
Thanks to the CHPC Organizers for inviting me over to deliver a keynote on upcoming research challenges of deep learning in HPC.
Today’s presentation day for my paper on deep and wide architecture for tree structured data processing.
Check out the article on Arxiv here.
A paper on randomized neural networks for preference learning with physiological timeseries data has just been accepted for pubblication on the Neurocomputing journal. Congratulations to my Biobeats collaborators!
Randomized neural networks for preference learning with physiological data. In: Neurocomputing, vol. 298, pp. 9-20, 2018.
New upocoming special session: I am co-organizing a Deep Learning for Structured and Multimedia Information (DEEPSM) session at WCCI2018.
The session is meant to attract researchers working on the next generation of deep learning models for machine vision and multimedia information which are capable of extracting and processing information in a structured representation and/or with a multimodal nature.
Work in progress for securing sponsorship for best paper awards.
Deadline for paper submission: 15 January 2018.
Prospective contributors/participants can contact me (or another co-organizer) for details.
Organized by: Davide Bacciu (Università di Pisa, Italy), Silvio Jamil F. Guimarães (PUC Minas, Brazil) and Zenilton K. G. Patrocínio Jr (PUC Minas, Brazil).
Congratulations to four of my students who just finished their M.Sc. and B.Sc discussing ML theses!!
Antonio Carta studied how to use deep learning to help CERN physicists filtering out fake trajectory hints in high energy physics (in co-supervision with Felice Pantaleo).
Francesco Crecchi proposed the DropIn technique to make recurrent neural network resilient to missing input data at inference time.
Andrea Cossu extended Echo State Networks and the ReCoPy Python framework with unsupervised anomaly detection mechanisms for sequential data.
Finally, Maurizio Idini presented his work supervised by Paolo Cignoni and Marco Di Benedetto (Visual Computing Lab @ISTI-CNR) regarding range maps denoising by deep learning techniques.
Ad maiora!
Tuesday 26/09 I will be giving a keynote at Dell-EMC Accelerating Understanding Summit on upcoming trends and challenges of Deep Learning.