We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code. Such neurosymbolic programs arise in many safety-critical domains. However, because they can use nondifferentiable operations, it is hard to learn their parameters using existing gradient-based approaches to safe learning. Our approach to this problem, Differentiable Symbolic Execution (DSE), samples control flow paths in a program, symbolically constructs worst-case "safety losses" along these paths, and backpropagates the gradients of these losses through program operations using a generalization of the REINFORCE estimator. We evaluate the method on a mix of synthetic tasks and real-world benchmarks. Our experiments show that DSE significantly outperforms the state-of-the-art DiffAI method on these tasks.
City, University of London（伦敦大学城市学院）；Federal University of Rio Grande do Sul（南里奥格兰德联邦大学）
Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning and for sound explainability. Neural-symbolic computing has been an active area of research for many years seeking to bring together robust learning in neural networks with reasoning and explainability v…
Department of Computer Science and Leuven.AI, KU Leuven, Belgium（1 计算机科学系和 Leuven.AI，KU Leuven，比利时）；Centre for Applied Autonomous Sensor Systems (AASS), Örebro University, Sweden（3 应用自主传感器系统中心（AASS），Örebro大学，瑞典）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Intel Labs China（英特尔中国研究院）；Shanghai Jiao Tong University（上海交通大学）
The booming of electric vehicles demands efficient battery disassembly for recycling to be environment-friendly. Currently, battery disassembly is still primarily done by humans, probably assisted by robots, due to the unstructured environment and high uncertainties. It is highly desirable to design autonomous solutions to improve work efficiency and lower human risks in high voltage and toxic environments. This paper proposes a novel neurosymbolic method, which augments the traditional Variational Autoencoder (VAE) model to learn symbolic operators based on raw sensory inputs and their relati…
Neurosymbolic AI for Travel Demand Prediction: Integrating Decision Tree Rules into Neural Networks
Department of Information Systems University of Maryland Baltimore County Baltimore, MD, US（信息系统系马里兰大学巴尔的摩县）；Department of Mechanical Engineering Baylor University Waco,TX, US（机械工程系贝勒大学）
California Institute of Technology（加州理工学院）；Northwestern University Feinberg School of Medicine（西北大学范伯格医学院）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specific language. Our framework naturally incorporates symbolic expert knowledge into the learning process, which leads to more interpretable and factorized latent representations compared to fully neural encoders. We integrate modern program synthesis techniques with the variational autoencoding (VAE) framework, in order to learn a neurosymbolic encoder in conjunction with a standard decoder. The programmatic description…
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. We identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science: to enable the use of NP broadly f…
Neurosymbolic Artificial Intelligence (NSAI) based Algorithm for predicting the Impact Strength of Additive Manufactured Polylactic Acid (PLA) Specimens
School of Industrial and Information Engineering, Politecnico Di Milano（米兰理工大学工业与信息工程学院）；Symbiosis Institute of Technology（共生技术学院）
University of Arizona（亚利桑那大学）；Microsoft Research（微软研究院）；Allen Institute for AI（艾伦人工智能研究所）
In this work, we explore techniques for augmenting interactive agents with information from symbolic modules, much like humans use tools like calculators and GPS systems to assist with arithmetic and navigation. We test our agent's abilities in text games -- challenging benchmarks for evaluating the multi-step reasoning abilities of game agents in grounded, language-based environments. Our experimental study indicates that injecting the actions from these symbolic modules into the action space of a behavior cloned transformer agent increases performance on four text game benchmarks that test a…
The symbolic AI community is increasingly trying to embrace machine learning in neuro-symbolic architectures, yet is still struggling due to cultural barriers. To break the barrier, this rather opinionated personal memo attempts to explain and rectify the conventions in Statistics, Machine Learning, and Deep Learning from the viewpoint of outsiders. It provides a step-by-step protocol for designing a machine learning system that satisfies a minimum theoretical guarantee necessary for being taken seriously by the symbolic AI community, i.e., it discusses "in what condition we can stop worrying …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
We consider the problem of combining machine learning models to perform higher-level cognitive tasks with clear specifications. We propose the novel problem of Visual Discrimination Puzzles (VDP) that requires finding interpretable discriminators that classify images according to a logical specification. Humans can solve these puzzles with ease and they give robust, verifiable, and interpretable discriminators as answers. We propose a compositional neurosymbolic framework that combines a neural network to detect objects and relationships with a symbolic learner that finds interpretable discrim…
NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models
Department of Computer Science, AI Institute, University of South Carolina（南卡罗来纳大学计算机科学系，人工智能研究所）；Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校计算机科学与电气工程系）；Department of Computer Science and Engineering, The Ohio State University（俄亥俄州立大学计算机科学与工程系）
Neurosymbolic Retrievers for Retrieval-augmented Generation
Dept. of CSEE University of Maryland Baltimore County, Maryland, USA（电子工程系大学马里兰大学巴尔的摩县）；Dept. of CSEE University of Maryland Baltimore County, MD, USA（电子工程系大学马里兰大学巴尔的摩县）
The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
Politecnico di Milano（米兰理工大学）；ELLIS Institute Finland（芬兰ELLIS研究所）；Åbo Akademi University（奥博 Akademi 大学）；Samsung AI（三星人工智能研究院）；Delft University of Technology（代尔夫特理工大学）；Stony Brook University（石溪大学）；Politecnico di Torino（都灵理工大学）；University of Stuttgart（斯图加特大学）；Graz University of Technology（格拉茨工业大学）；Lockheed Martin, Advanced Technology Labs（洛克希德·马丁公司先进技术实验室）；BrainCreators（BrainCreators公司）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）；UCLA（加利福尼亚大学洛杉矶分校）
A Domain-Agnostic Neurosymbolic Approach for Big Social Data Analysis: Evaluating Mental Health Sentiment on Social Media during COVID-19
AI Institute, University of South Carolina（南卡罗来纳大学AI研究所）；University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；Institute for Insight, Georgia State University（佐治亚州立大学洞察研究所）；Wright State University（莱特州立大学）
Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the program they want, but introduce small mistakes that yield broken formulas. These mistakes, which can be both syntactic and semantic, are hard for low-code users to identify and fix, even though they can be resolved with just a few edits. We formalize the problem of producing such edits as the last-mile repair problem. To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines s…
