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.
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)
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
Sorting out the last details of the Deep Learning demo on DNA sequence classification that I will be presenting next week @ Supercomputing 2016. Lots of fun playing around with Nvidia P100 accelerators.