RI: Small: Embracing Deep Neural Networks into Probabilistic Answer Set Programming

RI：小：将深度神经网络融入概率答案集编程

• 批准号: 2006747
• 负责人: Joohyung Lee
• 金额: $ 45.85万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006747&HistoricalAwards=false
• 关键词: RI; Small; Embracing; Deep; Neural

The integration of low-level perception with high-level reasoning is one of the fundamental problems in artificial intelligence. Today, the topic is revisited with the recent rise of deep neural networks. While deep learning excels in many perception tasks, it is not obvious how multiple aspects of commonsense reasoning, such as causality, defaults, abductive reasoning, and counterfactual reasoning, can be computed by neural networks. These subjects have been well-studied in the area of knowledge representation (KR) including answer set programming (ASP) but most KR formalisms are logic-oriented and do not incorporate high-dimensional feature space and pre-trained models for vision and text as in deep learning, which limits the applicability of KR in many practical applications involving uncertainty. The goal of the proposed research is to investigate a principled combination of knowledge representation, reasoning, and learning by integrating answer set programming with neural networks, which will enable representation, inference, and learning in both symbolic and sub-symbolic levels. The project will investigate two different approaches to integration. One is a loose coupling that is based on the concept of neural atoms which serves as an interface between the neural network output and the parameters for probabilistic answer set programming. The other is a tighter coupling method that obtains fuzzy-valued atomic facts from the neural network and applies the fuzzy answer set semantics on the vectorized representation. Not only these methods allow for applying symbolic reasoning on the neural network perception result but also allow for making use of logical rules in training a neural network so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by ASP rules. The success of the project will contribute to identifying fundamental issues in bridging the gap between knowledge representation and machine learning.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

低级感知与高级推理的融合是人工智能的基本问题之一。今天，随着深度神经网络最近的兴起，这个话题又被重新审视。虽然深度学习在许多感知任务中表现出色，但如何通过神经网络计算常识推理的多个方面（例如因果关系、默认值、溯因推理和反事实推理）尚不清楚。这些主题在包括答案集编程 (ASP) 在内的知识表示 (KR) 领域得到了深入研究，但大多数 KR 形式都是面向逻辑的，并且不包含高维特征空间以及视觉和文本的预训练模型。在深度学习中，这限制了 KR 在许多涉及不确定性的实际应用中的适用性。拟议研究的目标是通过将答案集编程与神经网络相结合来研究知识表示、推理和学习的原则性组合，这将实现符号和子符号级别的表示、推理和学习。该项目将研究两种不同的集成方法。一种是基于神经原子概念的松散耦合，神经原子充当神经网络输出和概率答案集编程参数之间的接口。另一种是更紧密的耦合方法，从神经网络获取模糊值原子事实，并将模糊答案集语义应用于矢量化表示。这些方法不仅允许对神经网络感知结果应用符号推理，而且允许在训练神经网络时使用逻辑规则，使得神经网络不仅从数据的隐式相关性中学习，而且从显式的复杂语义中学习ASP 规则表示的约束。该项目的成功将有助于确定弥合知识表示和机器学习之间差距的基本问题。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

A Simple Extension of Answer Set Programs to Embrace Neural Networks (Extended Abstract)

答案集程序的简单扩展以支持神经网络（扩展摘要）

• DOI: 10.4204/eptcs.325
• 发表时间: 2020-09
• 期刊: Electronic proceedings in theoretical computer science
• 作者: Yang, Zhun;Ishay, Adam;Lee, Joohyung
• 通讯作者: Lee, Joohyung

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

通过直通估计器将逻辑约束注入神经网络

• 发表时间: 2022-07
• 期刊: Proceedings of Machine Learning Research
• 作者: Yang, Zhun;Lee, Joohyung;Park, Chiyoun
• 通讯作者: Park, Chiyoun

Extending Answer Set Programs with Neural Networks

使用神经网络扩展答案集程序

• DOI: 10.4204/eptcs.325.41
• 发表时间: 2020-09
• 期刊: Electronic proceedings in theoretical computer science
• 作者: Yang; Zhun
• 通讯作者: Zhun

NeurASP: Embracing Neural Networks into Answer Set Programming

NeurASP：将神经网络纳入答案集编程

• DOI: 10.24963/ijcai.2020/243
• 发表时间: 2020-07
• 期刊: 29th International Joint Conference on Artificial Intelligence (IJCAI 2020
• 作者: Yang, Zhun;Ishay, Adam;Lee, Joohyung
• 通讯作者: Lee, Joohyung

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

通过直通估计器将逻辑约束注入神经网络

• 发表时间: 2022-07
• 期刊: International Conference on Machine Learning
• 作者: Yang, Zhun;Lee, Joohyung;Park, Chiyoun.
• 通讯作者: Park, Chiyoun.