Revealing structure components of the retina by deep learning networks
This work addresses the challenge of interpreting CNN features for neuroscience, specifically for understanding retinal circuits, though it is incremental as it builds on existing CNN models applied to neuronal response prediction.
The study tackled the problem of understanding what deep convolutional neural networks (CNNs) learn in relation to visual neuronal circuits by training CNNs with white noise images to predict neural responses from salamander retinal ganglion cells. The result showed that the learned convolutional filters resembled biological components of the retinal circuit, tiling the space of conventional receptive fields.
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.