Yearly Archives: 2017

Deep learning paper @SSCI2017

New paper accepted at forthcoming IEEE SSCI 2017 showing how you can go deep an wide on tree structured data processing using an hybrid neuro-probabilistic model.

Bacciu Davide: Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data. Proc. of the 2017 IEEE Symposium Series on Computational Intelligence (SSCI'17), IEEE, 2017.

Deep Learning special session at ESANN 2018

New upocoming special session: I am co-organizing a  Deep Learning in Bioinformatics and Medicine session at ESANN 2018.

The  session is intended for researchers (from both the deep learning and the bioinformatics communities) who develop, investigate, or apply deep learning methods on biomedical and chemistry data.

Deadline for paper submission: 20 November 2017.

Prospective contributors/participants can contact me (or another co-organizer) for details.

Organized by: Miguel Atencia (Universidad de Málaga, Spain), Davide Bacciu (Università di Pisa, Italy), Paulo J. G. Lisboa (Liverpool John Moores University, United Kingdom), Jose D. Martin, (Universitat de València, Spain), Ruxandra Stoean (University of Craiova, Romania), Alfredo Vellido (Universitat Politècnica de Catalunya, Spain)

New Graduates in the CI&ML group!

Congratulations to two M.Sc. students who have just completed their Computer Science master with two theses on machine learning.

Marco Podda studied how to help clinicians in predicting and understanding the causes of mortality in low birth-weight infants.

Cosimo Ragusa developed ReCoPy, a state-of-the-art neural networks library for Reservoir Computing in Python.

Dropout paper @IJCNN2017

How can you use Dropout to handle missing inputs in recurrent neural network? A nice paper by my student Francesco Crecchi is going to answer this at IJCNN2017

Bacciu Davide, Crecchi Francesco, Morelli Davide: DropIn: Making Neural Networks Robust to Missing Inputs by Dropout. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN 2017) , IEEE, 2017, ISBN: 978-1-5090-6182-2.

Paper accepted @ESANN2017

The joint research work with the Biobeats guys has produced an offspring which will be presented at ESANN 2017:

Bacciu Davide, Colombo Michele, Morelli Davide, Plans David: ELM Preference Learning for Physiological Data. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'17), i6doc.com, Louvain-la-Neuve, Belgium, 2017, ISBN: 978-2-875870384.

See you soon in Bruges!