Using machine learning and deep neural networks to automatically identify components of neural circuits in the visual system

Leuven - Master projects
|
About a week ago

Deep learning offers the opportunity to unravel the wiring of the brain from large neuronal anatomical data sets.

The shape and position of a neuron conveys critical information about its identity and function. The identification of cell types from structure is a classic method that relies on the time-consuming and labour intensive tracing of its structure. Recent advances in experimental and imaging techniques now allow the acquiring of data sets approation for data-driven approaches to neuronal circuit analysis feasible, with the caveat automated image processing pipelines become a necessity. Recent advances in deep neural networks and machine learning techniques have demonstrated the power of these techniques to reliably perform automated image recognition and segmentation online. This work 70 has begun to be translated to work in laboratory environments. The goal of this thesis/internship is to apply/develop these techniques to a set of imaging data where we would like to automatically identify to neuronal components involved in the processing of visual information. The suitable student should already be familiar with machine learning and imaging processing techniques, as well as have good knowledge of at least one programming language (preferably Julia, Python, MATLAB or C++).‚Äč

Type of project: Thesis, Combination of internship and thesis

Duration: 6-12 months

Required degree: Master of Science, Master of Engineering Science, Master of Bioengineering

Required background: Biomedical engineering, Computer Science, Physics

Supervising scientist(s): For further information or for application, please contact: Karl Farrow (Karl.Farrow@nerf.be)

Only for self-supporting students.

Share this on

truetrue

This website uses cookies for analytics purposes only without any commercial intent. Find out more here. Our privacy statement can be found here. Some content (videos, iframes, forms,...) on this website will only appear when you have accepted the cookies.

Accept cookies