3 papers
cs.LG2026
S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights
Yi-Shan Chu
Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geome…
cs.CV2025
Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
Haorui Yu, Yang Zhao, Yijia Chu +1
Vision-Language Models (VLMs) often appear culturally competent but rely on superficial pattern matching rather than genuine cultural understanding. We introduce a diagnostic frame…
stat.ML2025
From Universal Approximation Theorem to Tropical Geometry of Multi-Layer Perceptrons
Yi-Shan Chu, Yueh-Cheng Kuo
We revisit the Universal Approximation Theorem(UAT) through the lens of the tropical geometry of neural networks and introduce a constructive, geometry-aware initialization for sig…