中文
相关论文

相关论文: Knowledge-based Analogical Reasoning in Neuro-symb…

200 篇论文

Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have…

计算与语言 · 计算机科学 2021-06-11 Zeming Chen , Qiyue Gao , Lawrence S. Moss

Neuro-symbolic artificial intelligence is a novel area of AI research which seeks to combine traditional rules-based AI approaches with modern deep learning techniques. Neuro-symbolic models have already demonstrated the capability to…

人工智能 · 计算机科学 2021-09-14 Zachary Susskind , Bryce Arden , Lizy K. John , Patrick Stockton , Eugene B. John

Despite the practical success of Artificial Intelligence (AI), current neural AI algorithms face two significant issues. First, the decisions made by neural architectures are often prone to bias and brittleness. Second, when a chain of…

人工智能 · 计算机科学 2024-10-21 Sushmita Paul , Jinqiang Yu , Jip J. Dekker , Alexey Ignatiev , Peter J. Stuckey

The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence (AI). The deduction camp concerns itself with questions about the expressiveness of formal…

人工智能 · 计算机科学 2020-06-16 Vaishak Belle

The field of neuro-symbolic AI aims to benefit from the combination of neural networks and symbolic systems. A cornerstone of the field is the translation or encoding of symbolic knowledge into neural networks. Although many neuro-symbolic…

人工智能 · 计算机科学 2024-11-28 Simon Odense , Artur d'Avila Garcez

Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, and the extent to which they depend on structured reasoning…

计算与语言 · 计算机科学 2025-06-09 Yukang Yang , Declan Campbell , Kaixuan Huang , Mengdi Wang , Jonathan Cohen , Taylor Webb

Symbolic regression is a machine learning technique that can learn the governing formulas of data and thus has the potential to transform scientific discovery. However, symbolic regression is still limited in the complexity and…

机器学习 · 计算机科学 2023-05-30 Michael Zhang , Samuel Kim , Peter Y. Lu , Marin Soljačić

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

计算与语言 · 计算机科学 2023-11-07 Zeming Chen , Gail Weiss , Eric Mitchell , Asli Celikyilmaz , Antoine Bosselut

We introduce neural networks for end-to-end differentiable proving of queries to knowledge bases by operating on dense vector representations of symbols. These neural networks are constructed recursively by taking inspiration from the…

神经与进化计算 · 计算机科学 2017-12-05 Tim Rocktäschel , Sebastian Riedel

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…

Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results…

人工智能 · 计算机科学 2024-11-08 Xin Zhang , Victor S. Sheng

Imitation learning is a popular method for teaching robots new behaviors. However, most existing methods focus on teaching short, isolated skills rather than long, multi-step tasks. To bridge this gap, imitation learning algorithms must not…

人工智能 · 计算机科学 2025-11-04 Leon Keller , Daniel Tanneberg , Jan Peters

Combining machine learning with logic-based expert systems in order to get the best of both worlds are becoming increasingly popular. However, to what extent machine learning can already learn to reason over rule-based knowledge is still an…

神经与进化计算 · 计算机科学 2019-03-11 Nuri Cingillioglu , Alessandra Russo

In recent years, neuro-symbolic methods have become a popular and powerful approach that augments artificial intelligence systems with the capability to perform abstract, logical, and quantitative deductions with enhanced precision and…

人工智能 · 计算机科学 2025-02-04 Yuxuan Wu , Hideki Nakayama

In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can significantly streamline…

符号计算 · 计算机科学 2025-05-29 Weiting Liu , Jiaxu Cui , Jiao Hu , En Wang , Bo Yang

In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems…

机器学习 · 计算机科学 2023-06-27 Dongran Yu , Bo Yang , Dayou Liu , Hui Wang , Shirui Pan

Human reasoning can often be understood as an interplay between two systems: the intuitive and associative ("System 1") and the deliberative and logical ("System 2"). Neural sequence models -- which have been increasingly successful at…

人工智能 · 计算机科学 2021-12-16 Maxwell Nye , Michael Henry Tessler , Joshua B. Tenenbaum , Brenden M. Lake

Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined…

计算与语言 · 计算机科学 2025-10-09 Lei Xu , Pierre Beckmann , Marco Valentino , André Freitas

Neuro-symbolic AI is an effective method for improving the overall performance of AI models by combining the advantages of neural networks and symbolic learning. However, there are differences between the two in terms of how they process…

人工智能 · 计算机科学 2024-11-08 Xin Zhang , Victor S. Sheng

The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, are facing challenges surrounding unsustainable computational trajectories, limited robustness, and a lack of explainability. To develop…