Revealing structure components of the retina by deep learning networks

TL;DR

This paper demonstrates that deep learning models can be used to uncover structural components of retinal circuits by analyzing CNN features trained on neural response data from salamander retinal ganglion cells.

Contribution

It shows that CNN filters trained on neural responses can resemble biological retinal components, revealing circuit structures from complex neural data.

Findings

CNN filters resemble biological retinal components

Features tile the receptive field space of retinal ganglion cells

CNN can reveal neuronal circuit structures

Abstract

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is still no clear understanding of what CNNs learn in terms of visual neuronal circuits. Visualizing CNN's features to obtain possible connections to neuronscience underpinnings is not easy due to highly complex circuits from the retina to higher visual cortex. Here we address this issue by focusing on single retinal ganglion cells with a simple model and electrophysiological recordings from salamanders. By training CNNs with white noise images to predicate neural responses, we found that convolutional filters learned in the end are resembling to biological components of the retinal circuit. Features represented by these filters tile the space of conventional receptive field of retinal ganglion cells. These results suggest that CNN could be used to reveal structure components of neuronal circuits.