List of Projects – Spring 2019
Model-based surprise analysis of a BCI task
The goal of this project is to study the EEG signals measured from a BCI (Brain computer interface) task. First the student will decipher the P300 signal. In a second time
the student should implement a surprise framework, previously developed in the lab, for the BCI task and finally compare the experimental data with the theoretical approach.
Requirement: Signal processing, machine learning, familiarity with statistics, knowledge in Matlab or python.
Please send your CV and an up-to-date grade sheet of results to Martin Barry.
Fitting single-neuron models to data
Experimental data on responses of single neurons to current input is available at the ALLEN institute. The team in the Allen just had a recent paper in Nature Communications (Corinne Teeter et al. with
Christof Koch). In the LCN we have alternative algorithms for fitting neuron models to data (Pozzorini et al., Mensi et al. 2013,2015,2016) and it would be great to compare the results of the LCN fitting
procedure to theirs on the same data. Adaptations of the existing algorithm and some extra thinking are most necessary, since the nature of experimental data is a bit different from the one assumed by the
current LCN algorithms. The ideal candidate has taken the class ‘Neural Networks and Biological Modeling’ with excellent grades.
Supervisor: Wulfram Gerstner
Exploration of deep networks
Based on the discussion in the class on Artificial Neural Networks, the following topics can be proposed for further exploration(i) a variant of batch update
(ii) a variant of RMSprop
This project is open for one or maximum two students. Profile of candidate: EPFL master student in Computer Science (or related subject) who has followed the class ‘Artificial Neural Networks’ (or similar) in spring 2018.