Project Overview
Developing a brain-supervised artificial neural network to gain insight into how the brain extracts behaviorally relevant information
Department(s)
Neuroscience
Psychological and Brain Sciences
Mathematics
Abstract
The neural representation of visual information is not a static pattern, but instead undergoes multiple transformations over time (Hansen et al., 2021), and supports different feature use with differing task demands (Greene & Hansen, 2020). However, exactly how task-relevant information is built up by the brain and subsequently used by the observer is only vaguely understood. My lab is currently developing a novel convolutional neural network (CNN) where the convolutional layers are independently supervised by brain responses at different time points. The network is being desinged to use image information evaluated against neural responses to differentiate between two different tasks performed on identical real-world scenes. The role of this network is to provide insight into how the brain might extract behaviorally relevant infomration to support task completion.
Student Qualifications
Must be *highly* motivated and intellectually curious. Successful completion of NEUR 170 or PSYC 275 is required. Having completed additional courses in computer science and/or mathematics would be ideal.
Number of Student Researchers
2 students
Project Length
10 weeks
Applications open on 10/03/2023 and close on 02/28/2024