TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modeling

2025-08-06

AI Summary

Traditional artificial neural networks (ANNs) modeling primate visual cortex neglect temporal dynamics, resulting in low biological plausibility and degraded task performance. To address this, we propose Topo-SNN—a topologically organized deep spiking neural network—introducing the first scalable, cortex-inspired topological architecture for SNNs. By incorporating a spatiotemporal constraint (STC) loss function, Topo-SNN jointly optimizes hierarchical feature learning and self-organizing topographic mapping, explicitly encoding functional parcellation under spatiotemporal dynamics. On ImageNet, Topo-SNN maintains lossless accuracy (zero top-1 accuracy degradation), reducing performance drop by 3% relative to TopoNet, while significantly improving brain similarity, adversarial robustness, and neurobiological fidelity. Our key contribution lies in revealing how topological structure, synergized with spike-timing-dependent mechanisms, enables stable encoding of dynamic visual inputs—establishing a novel paradigm for brain-inspired visual computation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Representation Learning for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The primate visual cortex exhibits topographic organization, where functionally similar neurons are spatially clustered, a structure widely believed to enhance neural processing efficiency. While prior works have demonstrated that conventional deep ANNs can develop topographic representations, these models largely neglect crucial temporal dynamics. This oversight often leads to significant performance degradation in tasks like object recognition and compromises their biological fidelity. To address this, we leverage spiking neural networks (SNNs), which inherently capture spike-based temporal dynamics and offer enhanced biological plausibility. We propose a novel Spatio-Temporal Constraints (STC) loss function for topographic deep spiking neural networks (TDSNNs), successfully replicating the hierarchical spatial functional organization observed in the primate visual cortex from low-level sensory input to high-level abstract representations. Our results show that STC effectively generates representative topographic features across simulated visual cortical areas. While introducing topography typically leads to significant performance degradation in ANNs, our spiking architecture exhibits a remarkably small performance drop (No drop in ImageNet top-1 accuracy, compared to a 3% drop observed in TopoNet, which is the best-performing topographic ANN so far) and outperforms topographic ANNs in brain-likeness. We also reveal that topographic organization facilitates efficient and stable temporal information processing via the spike mechanism in TDSNNs, contributing to model robustness. These findings suggest that TDSNNs offer a compelling balance between computational performance and brain-like features, providing not only a framework for interpreting neural science phenomena but also novel insights for designing more efficient and robust deep learning models.

Problem

• Model topographic organization in primate visual cortex
• Address performance drop in topographic deep ANNs
• Enhance biological fidelity with spiking neural networks

Innovation

• Spiking neural networks for temporal dynamics
• Spatio-Temporal Constraints loss function
• Topographic organization enhances spike processing