Skip to main content

Research Repository

Advanced Search

Decoding of human identity by computer vision and neuronal vision

Zhang, Yipeng; Aghajan, Zahra M.; Ison, Matias; Lu, Qiujing; Tang, Hanlin; Kalender, Guldamla; Monsoor, Tonmoy; Zheng, Jie; Kreiman, Gabriel; Roychowdhury, Vwani; Fried, Itzhak

Decoding of human identity by computer vision and neuronal vision Thumbnail


Authors

Yipeng Zhang

Zahra M. Aghajan

Qiujing Lu

Hanlin Tang

Guldamla Kalender

Tonmoy Monsoor

Jie Zheng

Gabriel Kreiman

Vwani Roychowdhury

Itzhak Fried



Abstract

Extracting meaning from a dynamic and variable flow of incoming information is a major goal of both natural and artificial intelligence. Computer vision (CV) guided by deep learning (DL) has made significant strides in recognizing a specific identity despite highly variable attributes. This is the same challenge faced by the nervous system and partially addressed by the concept cells—neurons exhibiting selective firing in response to specific persons/places, described in the human medial temporal lobe (MTL) ⁠. Yet, access to neurons representing a particular concept is limited due to these neurons’ sparse coding. It is conceivable, however, that the information required for such decoding is present in relatively small neuronal populations. To evaluate how well neuronal populations encode identity information in natural settings, we recorded neuronal activity from multiple brain regions of nine neurosurgical epilepsy patients implanted with depth electrodes, while the subjects watched an episode of the TV series “24”. First, we devised a minimally supervised CV algorithm (with comparable performance against manually-labeled data) to detect the most prevalent characters (above 1% overall appearance) in each frame. Next, we implemented DL models that used the time-varying population neural data as inputs and decoded the visual presence of the four main characters throughout the episode. This methodology allowed us to compare “computer vision” with “neuronal vision”—footprints associated with each character present in the activity of a subset of neurons—and identify the brain regions that contributed to this decoding process. We then tested the DL models during a recognition memory task following movie viewing where subjects were asked to recognize clip segments from the presented episode. DL model activations were not only modulated by the presence of the corresponding characters but also by participants’ subjective memory of whether they had seen the clip segment, and by the associative strengths of the characters in the narrative plot. The described approach can offer novel ways to probe the representation of concepts in time-evolving dynamic behavioral tasks. Further, the results suggest that the information required to robustly decode concepts is present in the population activity of only tens of neurons even in brain regions beyond MTL.

Citation

Zhang, Y., Aghajan, Z. M., Ison, M., Lu, Q., Tang, H., Kalender, G., …Fried, I. (2023). Decoding of human identity by computer vision and neuronal vision. Scientific Reports, 13(1), Article 651. https://doi.org/10.1038/s41598-022-26946-w

Journal Article Type Article
Acceptance Date Dec 22, 2022
Online Publication Date Jan 12, 2023
Publication Date 2023
Deposit Date Mar 14, 2023
Publicly Available Date Mar 17, 2023
Journal Scientific Reports
Electronic ISSN 2045-2322
Publisher Springer Science and Business Media LLC
Peer Reviewed Peer Reviewed
Volume 13
Issue 1
Article Number 651
DOI https://doi.org/10.1038/s41598-022-26946-w
Public URL https://nottingham-repository.worktribe.com/output/16216513
Additional Information Received: 8 February 2022; Accepted: 22 December 2022; First Online: 12 January 2023; : The authors declare no competing interests.

Files




You might also like



Downloadable Citations