Sawant, Y and Kundu, JN and Radhakrishnan, VB and Sridharan, D (2022) A Midbrain Inspired Recurrent Neural Network Model for Robust Change Detection. In: Journal of Neuroscience, 42 (44). pp. 8262-8283.
|
PDF
jou_neu_42-44_8262 - 8283_2022.pdf - Published Version Download (2MB) | Preview |
Abstract
We present a biologically inspired recurrent neural network (RNN) that efficiently detects changes in natural images. The model features sparse, topographic connectivity (st-RNN), closely modeled on the circuit architecture of a “midbrain attention network.” We deployed the st-RNN in a challenging change blindness task, in which changes must be detected in a discontinuous sequence of images. Compared with a conventional RNN, the st-RNN learned 9x faster and achieved state-of-the-art performance with 15x fewer connections. An analysis of low-dimensional dynamics revealed putative circuit mechanisms, including a critical role for a global inhibitory (GI) motif, for successful change detection. The model reproduced key experimental phenomena, including midbrain neurons’ sensitivity to dynamic stimuli, neural signatures of stimulus competition, as well as hallmark behavioral effects of midbrain microstimulation. Finally, the model accurately predicted human gaze fixations in a change blindness experiment, surpassing state-of-the-art saliency-based methods. The st-RNN provides a novel deep learning model for linking neural computations underlying change detection with psychophysical mechanisms.
| Item Type: | Journal Article |
|---|---|
| Publication: | Journal of Neuroscience |
| Publisher: | Society for Neuroscience |
| Additional Information: | The copyright for this article belongs to Society for Neuroscience. |
| Keywords: | adult; Article; change blindness task; controlled study; female; functional connectivity; gaze; global inhibition; human; human cell; human experiment; information processing; male; mesencephalon; normal human; perception test; receptive field; recurrent neural network; saccadic eye movement; stimulus response; superior colliculus; task performance; topographic connectivity; blindness; brain; mesencephalon, Blindness; Brain; Humans; Mesencephalon; Neural Networks, Computer |
| Department/Centre: | Division of Biological Sciences > Centre for Neuroscience Division of Electrical Sciences > Computer Science & Automation Division of Interdisciplinary Sciences > Computational and Data Sciences |
| Date Deposited: | 01 Jan 2023 07:34 |
| Last Modified: | 01 Jan 2023 07:34 |
| URI: | https://eprints.iisc.ac.in/id/eprint/78650 |
Actions (login required)
 |
View Item |
