collaborators

6 papers

cs.LG2025

Closed-form Solutions: A New Perspective on Solving Differential Equations

Shu Wei, Yanjie Li, Lina Yu +8

The quest for analytical solutions to differential equations has traditionally been constrained by the need for extensive mathematical expertise. Machine learning methods like gene…

cs.LG2024

MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation Functions

Yanjie Li, Weijun Li, Lina Yu +6

Mathematical formulas serve as the means of communication between humans and nature, encapsulating the operational laws governing natural phenomena. The concise formulation of thes…

cs.LG2024

MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task

Yanjie Li, Jingyi Liu, Weijun Li +6

Mathematical formulas are the crystallization of human wisdom in exploring the laws of nature for thousands of years. Describing the complex laws of nature with a concise mathemati…

cs.AI2024

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure

Yanjie Li, Weijun Li, Lina Yu +14

Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable face…

cs.LG2024

DN-CL: Deep Symbolic Regression against Noise via Contrastive Learning

Jingyi Liu, Yanjie Li, Lina Yu +6

Noise ubiquitously exists in signals due to numerous factors including physical, electronic, and environmental effects. Traditional methods of symbolic regression, such as genetic…

cs.LG2024

Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning

Yanjie Li, Weijun Li, Lina Yu +6

The mathematical formula is the human language to describe nature and is the essence of scientific research. Finding mathematical formulas from observational data is a major demand…