6 papers
Efficient Approximation to Analytic and functions by Height-Augmented ReLU Networks
ZeYu Li, FengLei Fan, TieYong Zeng
This work addresses two fundamental limitations in neural network approximation theory. We demonstrate that a three-dimensional network architecture enables a significantly more ef…
Hyper-Compression: Model Compression via Hyperfunction
Fenglei Fan, Juntong Fan, Dayang Wang +5
The rapid growth of large models' size has far outpaced that of computing resources. To bridge this gap, encouraged by the parsimonious relationship between genotype and phenotype…
Neural Network Approximation: A View from Polytope Decomposition
ZeYu Li, ShiJun Zhang, TieYong Zeng +1
Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most ex…
Large Language Model Evaluated Stand-alone Attention-Assisted Graph Neural Network with Spatial and Structural Information Interaction for Precise Endoscopic Image Segmentation
Juntong Fan, Shuyi Fan, Debesh Jha +4
Accurate endoscopic image segmentation on the polyps is critical for early colorectal cancer detection. However, this task remains challenging due to low contrast with surrounding…
An Efficient Algorithm for Vertex Enumeration of Arrangement
Zelin Dong, Fenglei Fan, Huan Xiong +1
This paper presents a state-of-the-art algorithm for the vertex enumeration problem of arrangements, which is based on the proposed new pivot rule, called the Zero rule. The Zero r…
Rethink Deep Learning with Invariance in Data Representation
Shuren Qi, Fei Wang, Tieyong Zeng +1
Integrating invariance into data representations is a principled design in intelligent systems and web applications. Representations play a fundamental role, where systems and appl…