Deep learning to probe neural correlates of music processing

Thielen, J.

Deep learning to probe neural correlates of music processing

Files

Thielen, J._MSc_Thesis.pdf (1.94 MB)

Authors

Thielen, J.

Issue Date

2016-08-22

Language

en

Abstract

with increasingly more complex features represented at more downstream areas along the cortical sheet. This has been best known for the visual cortex, but not so much for the auditory cortex. Recent advances in artificial neural networks allow the end-to-end learning of models for solving problems such as automated music tag prediction. Here, we trained a residual neural network to predict tags of natural music stimuli. In turn, the trained model was used to probe neural representations of music across the cortical sheet. Using a searchlight representational similarity analysis we revealed a representational gradient across the Superior Temporal Gyrus (STG). This gradient extended from Planum Polare, which was more sensitive to complex feature representations, to central STG, which was more sensitive to simple feature representations, to Planum Temporale, which was again more sensitive to complex features. The results imply low-level processing around primary auditory cortex with a broad auditory association area around it along STG. Keywords: deep learning, music processing, functional magnetic resonance imaging, representational similarity analysis

URI

http://hdl.handle.net/123456789/2636

Supervisor

Gerven, M.A.J. van

Guclu, U.

Faculty

Faculteit der Sociale Wetenschappen