Implementing Fixational Eye Movement in a Recurrent Neural Network using Reinforcement Learning to achieve Super Resolution

Sonntag, Lukas

Implementing Fixational Eye Movement in a Recurrent Neural Network using Reinforcement Learning to achieve Super Resolution

Files

Sonntag 4839005-2021.pdf (779.44 KB)

Authors

Sonntag, Lukas

Issue Date

2021-01-29

Language

en

URI

https://theses.ubn.ru.nl/handle/123456789/15762

Abstract

My experiment explored Fixational Eye Movements' benefits in a Classification task with input with partially destroyed information. Rucci et al. findings suggest that FEMs play a crucial role in visual perception, especially when it comes to high-frequency data. Only a small part of the retina called the foveola can capture the full details of high-frequency input for many organisms like humans. To see in high-resolution with this physical limitation, we have to efficiently shift the input over this sensitive area. This unconscious process is called FEMs. In my experiment, I succeeded in learning an RNN the benefits of FEMs via Reinforcement learning. I could replicate some of Rucci et al. results and find evidence that FEM's are not just a useless bug.