Data-driven ANN-based visual decoding enables unsupervised functional alignment

2026/01/08 by Xin-Ya Zhang, Hang Lin, Zeyu Deng +3 · 1 voice
Engineering · Neuroscience · #Advanced Memory and Neural Computing #EEG and Brain-Computer Interfaces #Face Recognition and Perception

paper · pdf · doi:10.1038/s42003-025-09486-7

openalex publication_date 2026/01/08 · openalex created_date 2026/01/09 · openalex updated_date 2026/07/29

Abstract

Artificial neural networks (ANNs) offer a data-driven approach to reveal brain regional functions without explicit supervision. Here, we demonstrate that an ANN trained to decode visual stimuli from multi-unit spiking activity in monkeys, can not only reconstruct complex and dynamic scenes, but also spontaneously align with canonical cortical visual functions. Without any region-specific functional priors, the model identifies key brain areas associated with shape, color, and motion processing. We provide strong evidence that, despite low train-test dataset correlation at the recording-site level, the ANN-based model is able to learn task-relevant representations embedded at a high-dimensional population level and achieve reliable decoding performance. Furthermore, by inverting the architecture and retraining, we show that the same network can predict region-specific spiking patterns from visual input, indicating a reciprocal relationship between encoding and decoding. These findings shed light on ANN-based visual decoding as a powerful framework for unsupervised functional alignment in neural systems.

Citations

• Neural Basis of a Perceptual Decision in the Parietal Cortex (Area LIP) of the Rhesus Monkey
• SciPy 1.0: fundamental algorithms for scientific computing in Python
• The cortical critical power law balances energy and information in an optimal fashion
• MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
• Automated Learning Rate Scheduler for Large-batch Training
• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• Generic decoding of seen and imagined objects using hierarchical visual features
• STRUCTURE AND FUNCTION OF VISUAL AREA MT
• An Integrative Theory of Prefrontal Cortex Function

Discussions

• Zhang, XY., Lin, H., Deng, Z. Siegel, M., Miller, E.K., and Yan, G. (2026) Data-driven ANN-based visual decoding enables unsupervised functional alignment. Communications Biology, doi.org/10.1038/s420 [bsky, 4 points, 0 comments]

Related

• Cross-Modal Alignment between Visual Stimuli and Neural Responses in the Visual Cortex
• Spiking Neural Networks for fMRI-Based Visual Semantic Decoding
• Uncovering Brain-Like Hierarchical Patterns in Vision-Language Models through fMRI-Based Neural Encoding
• TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modeling
• Relating CNNs with brain: Challenges and findings