Masters students are welcome to reach out to discuss potential research opportunities, for semester projects or the masters thesis.
Technical advancements in modern neuroscience make it now routine to record thousands of neurons simultaneously in behaving animals. A core method is calcium imaging, which uses genetically encoded calcium sensors and fluorescence microscopy to generate video data of neural calcium fluctuations, a proxy for neural activity. Analysis of calcium imaging videos is a computationally-intensive problem, as the pixel-footprint of individual neurons must be segmented and their activity extracted from noisy video data and de-mixed from surrounding cells and neuropil. Rapid feature extraction from imaging is a valuable step toward closed-loop experimental designs requiring near-real-time decoding of brain signals, such as brain-computer-interfaces.
In this project, we will explore methods to build a fast pipeline to compress and extract features directly from streaming video data that can be used for downstream tasks. The extracted video features will then be used to perform real-time decoding from the mouse hippocampus, in order to predict animal position as they explore a virtual environment. We will build a benchmark suite from existing hippocampus calcium imaging datasets and test different computational pipelines and machine learning architectures for decoding animal position directly from video data, optimizing for speed and real-time applications, and comparing decoding accuracy to that obtained from “ground-truth” segmentation of individual neurons. This project is ideal for a motivated student interested in both neuroscience and machine learning.
For more information please contact daniel.molinuevogomez@epfl.ch to schedule a meeting.
Mental time-travel is the process of vividly remembering past personal experiences or imagining oneself in a future situation. Whereas humans can be asked to describe what they experience during mental time-travel, indirect approaches are needed to investigate whether mental time-travel exists in other species. We study a class of behavioural tasks that humans can presumably solve using mental time-travel, and that feature a behavioral readout other than verbal descriptions of subjective experiences. For example, a subject may perform an action to prepare for an event in the near future, by recalling a related but unique prior episode where they were unprepared.
In this project, we will design simple video game implementations of this behavioral paradigm, to study in rodent and human subjects. The project consists of four tasks. First, design and test implementations of the task using the Unity game engine. Second, run pilot human behavioural experiments with lab members and friends. Third, run the experiment online (e.g. on prolific.co) or with EPFL students. Four, analyse the behavioural data.
Good programming skills are a strict requirement; familiarity with Unity is an asset but not required. Interested students should send their application, including CV and grades, to both james.priestley@epfl.ch and johanni.brea@epfl.ch.
This project can also be done as a Semester project.