# Learning an attention model in an artificial visual system

## TL;DR

This paper presents an artificial visual system using a recurrent neural network trained with reinforcement learning to emulate human attention mechanisms, focusing on regions of interest for classification tasks.

## Contribution

It introduces a novel attention model within an artificial visual system that mimics human eye movements and attention, trained via reinforcement learning.

## Key findings

- Model exhibits human-like saccadic eye movements
- System effectively attends to relevant regions for classification
- Predicts new phenomena consistent with biological observations

## Abstract

The Human visual perception of the world is of a large fixed image that is highly detailed and sharp. However, receptor density in the retina is not uniform: a small central region called the fovea is very dense and exhibits high resolution, whereas a peripheral region around it has much lower spatial resolution. Thus, contrary to our perception, we are only able to observe a very small region around the line of sight with high resolution. The perception of a complete and stable view is aided by an attention mechanism that directs the eyes to the numerous points of interest within the scene. The eyes move between these targets in quick, unconscious movements, known as "saccades". Once a target is centered at the fovea, the eyes fixate for a fraction of a second while the visual system extracts the necessary information. An artificial visual system was built based on a fully recurrent neural network set within a reinforcement learning protocol, and learned to attend to regions of interest while solving a classification task. The model is consistent with several experimentally observed phenomena, and suggests novel predictions.