English
Related papers

Related papers: Assessing SATNet's Ability to Solve the Symbol Gro…

200 papers

Many experts argue that the future of artificial intelligence is limited by the field's ability to integrate symbolic logical reasoning into deep learning architectures. The recently proposed differentiable MAXSAT solver, SATNet, was a…

Artificial Intelligence · Computer Science 2021-06-22 Sever Topan , David Rolnick , Xujie Si

SATNet is a differentiable constraint solver with a custom backpropagation algorithm, which can be used as a layer in a deep-learning system. It is a promising proposal for bridging deep learning and logical reasoning. In fact, SATNet has…

Artificial Intelligence · Computer Science 2022-11-28 Sangho Lim , Eun-Gyeol Oh , Hongseok Yang

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability…

Machine Learning · Computer Science 2019-05-30 Po-Wei Wang , Priya L. Donti , Bryan Wilder , Zico Kolter

Bridging logical reasoning and deep learning is crucial for advanced AI systems. In this work, we present a new framework that addresses this goal by generating interpretable and verifiable logical rules through differentiable learning,…

Artificial Intelligence · Computer Science 2023-10-04 Zhaoyu Li , Jinpei Guo , Yuhe Jiang , Xujie Si

Neural models and symbolic algorithms have recently been combined for tasks requiring both perception and reasoning. Neural models ground perceptual input into a conceptual vocabulary, on which a classical reasoning algorithm is applied to…

Artificial Intelligence · Computer Science 2021-06-08 Ananye Agarwal , Pradeep Shenoy , Mausam

Neural-symbolic learning, an intersection of neural networks and symbolic reasoning, aims to blend neural networks' learning capabilities with symbolic AI's interpretability and reasoning. This paper introduces an approach designed to…

Artificial Intelligence · Computer Science 2025-06-10 Fadi Al Machot

Despite the recent successes of deep neural networks in various fields such as image and speech recognition, natural language processing, and reinforcement learning, we still face big challenges in bringing the power of numeric optimization…

Artificial Intelligence · Computer Science 2018-02-16 Fei Wang , Tiark Rompf

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and…

Machine Learning · Computer Science 2019-06-05 Di Chen , Yiwei Bai , Wenting Zhao , Sebastian Ament , John M. Gregoire , Carla P. Gomes

We introduce SATBench, a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems. Unlike prior work that focuses on inference…

Artificial Intelligence · Computer Science 2025-09-23 Anjiang Wei , Yuheng Wu , Yingjia Wan , Tarun Suresh , Huanmi Tan , Zhanke Zhou , Sanmi Koyejo , Ke Wang , Alex Aiken

While classical planning has been an active branch of AI, its applicability is limited to the tasks precisely modeled by humans. Fully automated high-level agents should be instead able to find a symbolic representation of an unknown…

Machine Learning · Computer Science 2019-03-28 Masataro Asai , Hiroshi Kajino

To handle AI tasks that combine perception and logical reasoning, recent work introduces Neurosymbolic Deep Neural Networks (NS-DNNs), which contain -- in addition to traditional neural layers -- symbolic layers: symbolic expressions (e.g.,…

Machine Learning · Computer Science 2024-02-07 Aaron Bembenek , Toby Murray

SAT provers are powerful tools for solving real-sized logic problems, but using them requires solid programming knowledge and may be seen w.r.t.\ logic like assembly language w.r.t.\ programming. Something like a high level language was…

Computers and Society · Computer Science 2015-07-15 Khaled Skander Ben Slimane , Alexis Comte , Olivier Gasquet , Abdelwahab Heba , Olivier Lezaud , Frederic Maris , Mael Valais

Neuro-symbolic learning generally consists of two separated worlds, i.e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a fundamental problem in AI. This paper presents a novel, softened…

Artificial Intelligence · Computer Science 2024-03-04 Zenan Li , Yuan Yao , Taolue Chen , Jingwei Xu , Chun Cao , Xiaoxing Ma , Jian Lü

In the ongoing quest for hybridizing discrete reasoning with neural nets, there is an increasing interest in neural architectures that can learn how to solve discrete reasoning or optimization problems from natural inputs, a task that Large…

Artificial Intelligence · Computer Science 2025-12-19 Marianne Defresne , Romain Gambardella , Sophie Barbe , Thomas Schiex

We propose an algorithm to explore the global optimization method, using SAT solvers, for training a neural net. Deep Neural Networks have achieved great feats in tasks like-image recognition, speech recognition, etc. Much of their success…

Machine Learning · Computer Science 2022-06-13 Subham S. Sahoo

Neuro-symbolic artificial intelligence (AI) systems typically couple a neural perception module to a discrete symbolic solver through a non-differentiable boundary, preventing constraint-satisfaction feedback from reaching the perception…

Artificial Intelligence · Computer Science 2026-03-20 Wael AbdAlmageed

It is feasible and practically-valuable to bridge the characteristics between graph neural networks (GNNs) and logical reasoning. Despite considerable efforts and successes witnessed to solve Boolean satisfiability (SAT), it remains a…

Machine Learning · Computer Science 2019-09-30 Ziliang Chen , Zhanfu Yang

Deep Neural Networks have achieved great success in some of the complex tasks that humans can do with ease. These include image recognition/classification, natural language processing, game playing etc. However, modern Neural Networks fail…

Artificial Intelligence · Computer Science 2023-07-04 Ashutosh Hathidara , Lalit Pandey

With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap…

Artificial Intelligence · Computer Science 2021-11-16 Minghao Liu , Fuqi Jia , Pei Huang , Fan Zhang , Yuchen Sun , Shaowei Cai , Feifei Ma , Jian Zhang

Answer set programming (ASP) is a logic programming formalism used in various areas of artificial intelligence like combinatorial problem solving and knowledge representation and reasoning. It is known that enhancing ASP with function…

Artificial Intelligence · Computer Science 2025-09-24 Lukas Gerlach , David Carral , Markus Hecher
‹ Prev 1 2 3 10 Next ›