arXiv · 2502.11809
Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective
Abstract
Bias formation in deep neural networks (DNNs) remains a critical yet poorly understood challenge, influencing both fairness and reliability in artificial intelligence systems. Inspired by the human visual system, which decouples object manifolds through hierarchical processing to achieve object recognition, we propose a geometric analysis framework linking the geometric complexity of class-specific perceptual manifolds in DNNs to model bias. Our findings reveal that differences in geometric complexity can lead to varying recognition capabilities across categories, introducing biases. To support this analysis, we present the Perceptual-Manifold-Geometry library, designed for calculating the geometric properties of perceptual manifolds. The toolkit has been downloaded and installed over 4,500 times. This work provides a novel geometric perspective on bias formation in modern learning systems and lays a theoretical foundation for developing more equitable and robust artificial intelligence.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yanbiao Ma, Bowei Liu, Andi Zhang. 2025-02-17. Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective. https://arxiv.org/abs/2502.11809
Cite the original work for its findings. Save a collection to share your selection of sources.