Theses of 2015

This it the list of theses defended in our group. The topics vary from single neuron model to psychological experiments in virtual reality!

Zurab Bzhalava, MSc
Exploring the animal GPS system: a machine learning approach to study the hippocampal function

bzhalava_msc we set to compare how well different machine learning algorithms are able to predict a rat’s position just based on its hippocampal neural activity <...> we analysed data recorded from an experiment where rats were trained to choose left or right direction in a 8-shaped maze while they were run- ning in a wheel. In this case we perform a dimensionality reduction of the neuronal data to visualize its dynamics during the decision time.

Martin Loginov, MSc
Beyond decoding: representational similarity analysis on fMRI data

loginov_msc In this thesis RSA is implemented on a well known fMRI dataset in neuroscience, that was produced by a studying the categorical representations of objects in the ventral temporal cortex of human subjects. We carry out RSA on this dataset using different notions of distance and give an overview of how the end results of the analysis are affected by each distance notion. In total 9 different distance measures were evaluated for calculating the similarity between activation patterns in fMRI data.

Taivo Pungas, BSc
Implementing and investigating a biologically realistic neuron model

pungas_bsc Calcium-based single neuron models have been shown to elicit different modes of synaptic plasticity. In the present study one such model was implemented and its learning behaviour studied. Behaviour of the implemented neuron agreed qualitatively with prior work in all regards except selectivity to correlation in input. The neuron was found to im- plement a linear filter responding linearly to partial presentations of learned pat- terns.

Anti Ingel, BSc
Control a Robot via VEP Using Emotiv EPOC

ingel_bsc This thesis describes an SSVEP-based BCI implemented as a practical part of this work. <...> The BCI implemented as a part of this thesis uses widely known PSDA and CCA feature extraction methods and introduces a new way to combine these methods. Combining different methods improves the performance of a BCI. The application was tested only superficially and the following results were obtained: 2.61 ± 0.28 s target detection time, 85.81 ± 6.39 % accuracy and 27.73 ± 5.11 bits/min ITR.

Kälver Kilvits, BSc
Toolbox for creating virtual reality environments for memory research

kilvits_bsc The main purpose of this thesis is to create a toolbox that enables to create memory experiments in virtual reality. The toolbox will have a random game room generator, level editor and an experiment creator. It will support four different types of memory experiment methods.

Markus Kängsepp, BSc
Virtual Reality Environment for Studying Change Blindness

kangsepp_bsc The aim of the present thesis is to develop a toolbox that allows one to easily prepare, reproduce and carry out change blindness experiments in virtual reality. For this, toolbox enables to design levels by modifying objects’ position, appearance and adding new ones. Also personalised experiments can be created and executed.

Rasmus Vahtra, BSc
Mobiilirakenduse loomine tehisnärvivõrgule (Mobile application for artificial neural network)

vahtra_bsc Projekti eesmärgiks on uurida tehisnärvivõrkude olemust ja töömehaanikat ning luua mobiilrakendus, mille abil saaks neid ära kasutada. Selleks uuriti lähemalt 2012. aastal korraldatud ImageNet 2012 konkursi võitjate loodud tehisnärvivõrku. Uurimise käigus tehti selgeks, mida tehisnärvivõrk endast kujutab, kuidas konkreetne CaffeNet mudel loodud on ja kuidas seda on treenitud. Sama mudelit kasutati ka käesoleva töö käigus loodud lahenduse loomises, mis võimaldab teha mobiilirakendusega foto ning rakendus näitab, mis selle foto peal on.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>