You are here



Amira Chekir is a PhD student in computer science, her work focuses on Diffusion MRI,Tractography, White Mater clustering and brain connectivity. She obtained her Master in Computer Science in 2011 from the University of Science and Technology of Algeria (USTHB).


At Rovereto Attention Workshop (RAW), Elena Kalinina presented a poster entitled "Shared patterns of object categorization in different cognitive processes: Cross-modal decoding vs. Statistical permutation test", a joint work with F.Pedregosa, V.Iacovella, E.Olivetti e P.Avesani. The authors proposed to frame the question of identifying shared activity patterns between different cognitive processes as statistical hypothesis testing and applied it to the data of an fMRI experiment that consisted of three cognitive tasks: Perception, Imagery and Visual Search.


Muhaddisa Barat Ali joins NILab as a 1st year PhD student of the XXXI cycle. She is going to do research on computational methods for brain connectivity analysis.


Nusrat Sharmin presented a poster entitled "Alignment of Tractograms as Linear Assignment Problem" at CDMRI 15 - workshop on computational diffusion MRI during MICCAI 2015.
MICCAI 2015 (18th International Conference on Medical Image Computing and Computer Assisted Interventions) was held in Munich, Germany from October 5th to October 9th.


The paper entitled "Non-parametric temporal modeling of the hemodynamic response function via a liquid state machine" was published in the Neural Networks journal together with H.Hazan, E.Kollis and M. Manevitz from the University of Haifa and D. Sona from the Italian Institute of Technology. The paper tries to overcome limitations created by common assumptions in the MRI data analysis by proposing a method wherein the HRF is learned directly from data rather than induced from its basic form assumed in advance.


18th International Conference on Image Analysis and Processing (ICIAP 2015) took place in Genova from Septermber 7th to September 11th. At the conference, Pouya Ghaemmaghami presented a poster entitled "Movie Genre Classification by Exploiting MEG Brain Signals".


The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML/PKDD 2015) took place in Porto, Portugal, from September 7th to September 11. At the conference, Paolo Avesani presented a paper entitled "Tractome: a visual data mining tool for brain connectivity analysis" - a joint work with Diana Porro, Emanuele Olivetti, Nusrat Sharmin, Thien Bao Nguyen and Eleftherios Garyfallidis.


In in September Issue of "Data Mining and Knowledge Discovery" Diana Porro published a paper entitled "Tractome: a visual data mining tool for brain connectivity analysis" - a joint work with Emanuele Olivetti, Nusrat Sharmin, Thien Bao Nguyen, Eleftherios Garyfallidis and Paolo Avesani.


The course on Advanced Topics in Machine Learning this year focused on Deep Learning. The Summer School was organized by the Section for cognitive systems (CogSys) at the Technical University of Denmark (Copenhagen) from August 24th to 28th. The course sessions covered both theoretical and technical programming aspects and popular topics of deep learning such as: Deep Convolutional Neural Networks, Deep Recurrent Neural Networks, GPU programming, Neural Networks and probability theories,and applications of deep architectures. Practical sessions provided a very comprehensive tutorial for popular tools for deep learning such as theano, Lasagne, and deeppy.


The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS) took place in Milano, Italy, in the period August 25th-29th, 2015. At the meeting, Diego Sona's group presented a paper entitled "Sleep-Stage Scoring in Mice: The Influence of Data Pre-Processing on a System's Performance".