Emergent neuronal mechanisms mediating covert attention in convolutional neural networks

• 成果类型: Article
• 署名作者: Srivastava, Sudhanshu; Wang, William Yang; Eckstein, Miguel P.
• 署名单位: University of California System; University of California Santa Barbara; University of California System; University of California Santa Barbara; University of California System; University of California Santa Barbara; University of California System; University of California Santa Barbara; University of California System; University of California Santa Barbara
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-8424; 1091-6490
• DOI: 10.1073/pnas.2411909122
• 发表日期: 2025-11-18
• 页码: e2411909122
• 关键词: covert visual attention; Bayesian ideal observer; convolutional neural networks; neuroscience; INCREASES CONTRAST SENSITIVITY; visual-attention; superior colliculus; ZOOM LENS; modulation; MODEL; performance; responses; search; decisions

摘要

Covert visual attention allows the brain to select different regions of the visual world without eye movements. Predictive cues of a target location orient covert attention and improve perceptual performance. In most computational models, researchers explicitly incorporate an attentional mechanism that alters processing at the attended location Here, we assess the emergent neuronal mechanisms of Convolutional Neural Networks (CNNs) that exhibit behavioral signatures of covert attention, despite lacking a built- in attention mechanism. We use neuroscience- inspired approaches to analyze 1.8 M units of CNNs trained on the cueing paradigm. Consistent with neurophysiology, we show early layers with retinotopic neurons separately tuned to the target or cue, and later layers with neurons with joint tuning and increased cue influence on target responses. gradual transitions. The cue influences the target sensitivity through four mechanisms. A BIO- like cue- weighted location summation, and three mechanisms absent in the BIO: an opponency across locations, a summation/opponency location combination, and interaction with the thresholding Rectified Linear Unit. Reanalyses of mice's superior colliculus neuronal activity during a cueing task show CNN- predicted but previously unreported cue- inhibitory, location- summation, and location- opponent cells in addition and a framework to identify new neuron types and emergent computational mechanisms contributing to perceptual behavior.