Master Thesis Projects

Master Thesis Projects are started once the complete master program is finished and all the credits have been obtained.
Projects for SSC and SIN students should last 4 months at the EPFL or 6 months in the industry or in another University.
Master Thesis Projects must be done individually.
Master Thesis Projects are worth 30 credits.
Students must have the approval of the Professor in charge of the laboratory before registering for the given project.

Link to the Academic Calendar

List of Projects – Spring 2019:

Associative memories and correlations

Human memory operates with associations. If you visited a famous place with your best friend, any postcard of that famous place will remind you of him or her. Experimental evidence suggests that associative memory is stored by cell assemblies that respond selectively to single concepts. Associations between different concepts are encoded in the overlap between the respective cell assemblies. Associative memory is traditionally modeled through attractor neural networks (ANN). Memory engrams are represented by binary or Gaussian patterns. In this project, the student will consider an ANN with Gaussian patterns and study how the stability of a single memory pattern is affected by the correlation with other patterns. This, so far, remains an open question and it is complementary to the more traditional study of ANNs with binary patterns. The student will first get to learn about the well-established literature on ANN. Secondly, using mean-field approximation, the student will derive analytic equations for the network dynamics in the case of correlated patterns. The goal is to look for a critical correlation Cˆ∗ (which corresponds to a percentage of shared neurons) above which patterns are not distinguishable.
Finally, the student will solve the equations he/she derived and compare his/her prediction with the full network simulation.

Requirements: Python programming (knowledge of Julialang is recommended but not necessary). Interested students should send grades and CV to Chiara Gastaldi.

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.

Please send your CV and an up-to-date grade sheet of results to Bernd Illing, Johanni Brea or Florian Colombo.