中文
相关论文

相关论文: Neuro-Symbolic AI for Analytical Solutions of Diff…

200 篇论文

Automated design of chemical formulations is a cornerstone of materials science, yet it requires navigating a high-dimensional combinatorial space involving discrete compositional choices and continuous geometric constraints. Existing Large…

人工智能 · 计算机科学 2026-04-17 Jiangyu Chen

The quest for analytical solutions to differential equations has traditionally been constrained by the need for extensive mathematical expertise. Machine learning methods like genetic algorithms have shown promise in this domain, but are…

机器学习 · 计算机科学 2025-07-22 Shu Wei , Yanjie Li , Lina Yu , Weijun Li , Min Wu , Linjun Sun , Jingyi Liu , Hong Qin , Yusong Deng , Jufeng Han , Yan Pang

When neural networks are used to solve differential equations, they usually produce solutions in the form of black-box functions that are not directly mathematically interpretable. We introduce a method for generating symbolic expressions…

机器学习 · 计算机科学 2020-11-05 Maysum Panju , Ali Ghodsi

We propose SymPlex, a reinforcement learning framework for discovering analytical symbolic solutions to partial differential equations (PDEs) without access to ground-truth expressions. SymPlex formulates symbolic PDE solving as…

机器学习 · 计算机科学 2026-02-04 Yesom Park , Annie C. Lu , Shao-Ching Huang , Qiyang Hu , Y. Sungtaek Ju , Stanley Osher

Understanding natural and engineered systems often relies on symbolic formulations, such as differential equations, which provide interpretability and transferability beyond black-box models. We introduce Latent Grammar Flow (LGF), a…

机器学习 · 计算机科学 2026-04-20 Karin Yu , Eleni Chatzi , Georgios Kissas

We describe a neural-based method for generating exact or approximate solutions to differential equations in the form of mathematical expressions. Unlike other neural methods, our system returns symbolic expressions that can be interpreted…

机器学习 · 计算机科学 2020-11-16 Maysum Panju , Kourosh Parand , Ali Ghodsi

This paper demonstrates that artificial intelligence can accelerate mathematical discovery by autonomously solving an open problem in theoretical physics. We present a neuro-symbolic system, combining the Gemini Deep Think large language…

人工智能 · 计算机科学 2026-03-06 Michael P. Brenner , Vincent Cohen-Addad , David Woodruff

Partial differential equations (PDEs) are ubiquitous in the world around us, modelling phenomena from heat and sound to quantum systems. Recent advances in deep learning have resulted in the development of powerful neural solvers; however,…

人工智能 · 计算机科学 2023-11-13 Yolanne Yi Ran Lee

Solving Partial Differential Equations (PDEs) is fundamental to numerous scientific and engineering disciplines. A common challenge arises from solving the PDE families, which are characterized by sharing an identical mathematical structure…

人工智能 · 计算机科学 2026-02-13 Yipeng Huang , Dejun Xu , Zexin Lin , Zhenzhong Wang , Min Jiang

Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order…

人工智能 · 计算机科学 2026-01-05 Keqin Xie

Neuro-symbolic artificial intelligence (NSAI) represents a transformative approach in artificial intelligence (AI) by combining deep learning's ability to handle large-scale and unstructured data with the structured reasoning of symbolic…

人工智能 · 计算机科学 2025-02-18 Oualid Bougzime , Samir Jabbar , Christophe Cruz , Frédéric Demoly

Neurosymbolic (NeSy) frameworks combine neural representations and learning with symbolic representations and reasoning. Combining the reasoning capacities, explainability, and interpretability of symbolic processing with the flexibility…

人工智能 · 计算机科学 2025-09-10 Sania Sinha , Tanawan Premsri , Danial Kamali , Parisa Kordjamshidi

Neuro-symbolic approaches to artificial intelligence, which combine neural networks with classical symbolic techniques, are growing in prominence, necessitating formal approaches to reason about their correctness. We propose a novel…

人工智能 · 计算机科学 2024-07-12 Rui Yan , Gabriel Santos , Gethin Norman , David Parker , Marta Kwiatkowska

It has been demonstrated that artificial neural networks like autoencoders or Siamese networks encode meaningful concepts in their latent spaces. However, there does not exist a comprehensive framework for retrieving this information in a…

机器学习 · 计算机科学 2025-09-29 Sebastian J. Wetzel , Zakaria Patel

Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of…

机器学习 · 计算机科学 2026-05-28 Akshaj Murhekar , Abhijit Mishra

Differential equations are widely used to describe complex dynamical systems with evolving parameters in nature and engineering. Effectively learning a family of maps from the parameter function to the system dynamics is of great…

机器学习 · 计算机科学 2025-03-12 Xin Li , Chengli Zhao , Xue Zhang , Xiaojun Duan

Motivated by the remarkable success of artificial intelligence (AI) across diverse fields, the application of AI to solve scientific problems, often formulated as partial differential equations (PDEs), has garnered increasing attention.…

机器学习 · 计算机科学 2025-10-21 Rohan Bhatnagar , Ling Liang , Krish Patel , Haizhao Yang

Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver…

计算与语言 · 计算机科学 2021-07-06 Jinghui Qin , Xiaodan Liang , Yining Hong , Jianheng Tang , Liang Lin

The working mechanisms of complex natural systems tend to abide by concise and profound partial differential equations (PDEs). Methods that directly mine equations from data are called PDE discovery, which reveals consistent physical laws…

机器学习 · 计算机科学 2023-03-17 Mengge Du , Yuntian Chen , Dongxiao Zhang

Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems, as interpretable symbolic techniques provide formal behaviour guarantees. The challenge is how to effectively integrate neural and symbolic computation, to…

人工智能 · 计算机科学 2024-02-06 Daniel Cunnington , Mark Law , Jorge Lobo , Alessandra Russo
‹ 上一页 1 2 3 10 下一页 ›