检索结果-内蒙古大学图书馆

35th Annual Conference on Neural Information Processing Systems (NeurIPS)

作者： Ahmed, Kareem Li, Tao Ton, Thy Guo, Quan Chang, Kai-Wei Kordjamshidi, Parisa Srikumar, Vivek Van den Broeck, Guy Singh, Sameer Univ Calif Los Angeles Los Angeles CA 90024 USA Univ Utah Salt Lake City UT USA Univ Calif Irvine Irvine CA USA Sichuan Univ Chengdu Peoples R China Michigan State Univ E Lansing MI USA

Deep learning excels at learning low-level task information from large amounts of data, but struggles with learning high-level domain knowledge, which can often be directly and succinctly expressed. In this work, we introduce Pylon, a neuro-symbolic training framework that builds on PyTorch to augment procedurally trained neural networks with declaratively specified knowledge. Pylon allows users to programmatically specify constraints as PyTorch functions, and compiles them into a differentiable loss, thus training predictive models that fit the data whilst satisfying the specified constraints. Pylon includes both exact as well as approximate compilers to efficiently compute the loss, employing fuzzy logic, sampling methods, and circuits, ensuring scalability even to complex models and constraints. A guiding principle in designing Pylon has been the ease with which any existing deep learning codebase can be extended to learn from constraints using only a few lines: a function expressing the constraint and a single line of code to compile it into a loss. We include case studies from natural language processing, computer vision, logical games, and knowledge graphs, that can be interactively trained, and highlights Pylon's usage.

关键词： Neuro-symbolic learning learning with constraints Deep learning

来源：评论

学校读者我要写书评

暂无评论

Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge 24

Error Detection and Constraint Recovery in Hierarchical Mult...

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Kricheli, Joshua Shay Vo, Khoa Datta, Aniruddha Ozgur, Spencer Shakarian, Paulo Arizona State Univ Tempe AZ 85287 USA

ISBN: (纸本)9798400704369

Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such work assumes the existence of such constraints a-priori. In this paper, we relax this strong assumption and present an approach based on Error Detection Rules (EDR) that allow for learning explainable rules about the failure modes of machine learning models. We show that these rules are not only effective in detecting when a machine learning classifier has made an error but also can be leveraged as constraints for HMC, thereby allowing the recovery of explainable constraints even if they are not provided. We show that our approach is effective in detecting machine learning errors and recovering constraints, is noise tolerant, and can function as a source of knowledge for neurosymbolic models on multiple datasets, including a newly introduced military vehicle recognition dataset.

关键词： Metacognitive AI learning with constraints Rule learning NeuroSymbolic AI Hierarchical Multi-label Classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid Loss for Hierarchical Multi-label Classification Network

Hybrid Loss for Hierarchical Multi-label Classification Netw...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Qi, Wenting Chelmis, Charalampos University at Albany Suny Department of Computer Science AlbanyNew York United States

ISBN: (纸本)9798350324457

Machine learning models for hierarchical multilabel classification (HMC) typically achieve low accuracy. This is because such models need not only predict multiple labels for each data instance, but also ensure that predicted labels conform to a given hierarchical structure. Existing state-of the-art strategies for HMC decouple the learning process from ensuring that predicted labels reside in a path of the hierarchy, thus inevitably degrading the overall classification accuracy. To address this limitation, we propose a novel loss function, which enables a model to encode both a global perspective of the class hierarchy, as well local class-relationships in adjacent hierarchical levels, to ensure that predictions align with the class hierarchy, both during training and testing. We demonstrate the superiority of the proposed approach against multiple state-of-the-art methods for HMC on 20 real-world datasets. © 2023 IEEE.

关键词： global loss learning with constraints local loss

来源：评论

学校读者我要写书评

暂无评论

Analyzing Differentiable Fuzzy Logic Operators

引用

ARTIFICIAL INTELLIGENCE 2022年 302卷 103602-103602页

作者： van Krieken, Emile Acar, Erman van Harmelen, Frank Vrije Univ Amsterdam Amsterdam Netherlands Civ AI Lab Amsterdam Netherlands

The AI community is increasingly putting its attention towards combining symbolic and neural approaches, as it is often argued that the strengths and weaknesses of these approaches are complementary. One recent trend in the literature is weakly supervised learning techniques that employ operators from fuzzy logics. In particular, these use prior background knowledge described in such logics to help the training of a neural network from unlabeled and noisy data. By interpreting logical symbols using neural networks, this background knowledge can be added to regular loss functions, hence making reasoning a part of learning. We study, both formally and empirically, how a large collection of logical operators from the fuzzy logic literature behave in a differentiable learning setting. We find that many of these operators, including some of the most well-known, are highly unsuitable in this setting. A further finding concerns the treatment of implication in these fuzzy logics, and shows a strong imbalance between gradients driven by the antecedent and the consequent of the implication. Furthermore, we introduce a new family of fuzzy implications (called sigmoidal implications) to tackle this phenomenon. Finally, we empirically show that it is possible to use Differentiable Fuzzy Logics for semi-supervised learning, and compare how different operators behave in practice. We find that, to achieve the largest performance improvement over a supervised baseline, we have to resort to non-standard combinations of logical operators which perform well in learning, but no longer satisfy the usual logical laws. (C) 2021 The Author(s). Published by Elsevier B.V.

关键词： Fuzzy logic Neural-symbolic AI learning with constraints

来源：评论

学校读者我要写书评

暂无评论

learning Bayesian network parameters under equivalence constraints

引用

ARTIFICIAL INTELLIGENCE 2017年 244卷 239-257页

作者： Yao, Tiansheng Choi, Arthur Darwiche, Adnan Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90095 USA

We propose a principled approach for learning parameters in Bayesian networks from incomplete datasets, where the examples of a dataset are subject to equivalence constraints. These equivalence constraints arise from datasets where examples are tied together, in that we may not know the value of a particular variable, but whatever that value is, we know it must be the same across different examples. We formalize the problem by defining the notion of a constrained dataset and a corresponding constrained likelihood that we seek to optimize. We further propose a new learning algorithm that can effectively learn more accurate Bayesian networks using equivalence constraints, which we demonstrate empirically. Moreover, we highlight how our general approach can be brought to bear on more specialized learning tasks, such as those in semi-supervised clustering and topic modeling, where more domain-specific approaches were previously developed. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Bayesian networks Parameter learning learning with constraints Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Structured learning modulo theories

引用

ARTIFICIAL INTELLIGENCE 2017年 244卷 166-187页

作者： Teso, Stefano Sebastiani, Roberto Passerini, Andrea Fdn Bruno Kessler DKM Data & Knowledge Management Unit Via Sommarive 18 I-138123 Povo TN Italy Univ Trento DISI Via Sommarive 5 I-38123 Povo TN Italy

Modeling problems containing a mixture of Boolean and numerical variables is a long-standing interest of Artificial Intelligence. However, performing inference and learning in hybrid domains is a particularly daunting task. The ability to model these kinds of domains is crucial in "learning to design" tasks, that is, learning applications where the goal is to learn from examples how to perform automatic de novo design of novel objects. In this paper we present Structured learning Modulo Theories, a max-margin approach for learning in hybrid domains based on Satisfiability Modulo Theories, which allows to combine Boolean reasoning and optimization over continuous linear arithmetical constraints. The main idea is to leverage a state-of-the-art generalized Satisfiability Modulo Theory solver for implementing the inference and separation oracles of Structured Output SVMs. We validate our method on artificial and real world scenarios. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Satisfiability modulo theory Structured-output support vector machines Optimization modulo theory Constructive machine learning learning with constraints

来源：评论

学校读者我要写书评

暂无评论

Semantic-based regularization for learning and inference

引用

ARTIFICIAL INTELLIGENCE 2017年 244卷 143-165页

作者： Diligenti, Michelangelo Gori, Marco Sacca, Claudio Univ Siena Dept Informat Engn & Math Via Roma 56 Siena Italy

This paper proposes a unified approach to learning from constraints, which integrates the ability of classical machine learning techniques to learn from continuous feature-based representations with the ability of reasoning using higher-level semantic knowledge typical of Statistical Relational learning. learning tasks are modeled in the general framework of multi-objective optimization, where a set of constraints must be satisfied in addition to the traditional smoothness regularization term. The constraints translate First Order Logic formulas, which can express learning-from-example supervisions and general prior knowledge about the environment by using fuzzy logic. By enforcing the constraints also on the test set, this paper presents a natural extension of the framework to perform collective classification. Interestingly, the theory holds for both the case of data represented by feature vectors and the case of data simply expressed by pattern identifiers, thus extending classic kernel machines and graph regularization, respectively. This paper also proposes a probabilistic interpretation of the proposed learning scheme, and highlights intriguing connections with probabilistic approaches like Markov Logic Networks. Experimental results on classic benchmarks provide clear evidence of the remarkable improvements that are obtained with respect to related approaches. (C) 2015 Elsevier B.V. All rights reserved.

关键词： learning with constraints Kernel machines FOL

来源：评论

学校读者我要写书评

暂无评论

Multitask Semi-supervised learning with constraints and Constraint Exceptions

Multitask Semi-supervised Learning with Constraints and Cons...

引用

20th International Conference on Artificial Neural Networks

作者： Maggini, Marco Papini, Tiziano Univ Siena Dipartimento Ingn Informaz I-53100 Siena Italy

ISBN: (纸本)9783642158247

Many applications require to jointly learn a set of related functions for which some a priori mutual constraints are known. In particular, we consider a multitask learning problem in which a set of constraints among the different tasks are know to hold in most cases. Basically, beside a set of supervised examples provided to learn each task, we assume that some background knowledge is available in the form of functions that define the admissible configurations of the task function outputs for almost each input. We exploit a semi supervised approach in which a potentially large set of unlabeled examples is used to enforce the constraints on a large region of the input space by means of a proper penalty function. However, since the constraints are known to be subject to exceptions and the inputs corresponding to these exceptions are not known a priori, we propose to embed a selection criterion in the penalty function that reduces the constraint effect on those points that are likely to yield an exception. We report some experiments on multi view object recognition showing the benefits of the proposed selection mechanism with respect to an uniform enforcement of the constraints.

关键词： Semi-supervised learning learning with constraints Multi-view object recognition Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Bayesian learning techniques: Application to neural networks with constraints on weight space 1

引用

13th Italian Workshop on Neural Nets (WIRN VIETRI 2002)

作者： Eleuteri, A Tagliaferri, R Milano, L Acernese, F De Laurentiis, M Univ Naples Federico II Dipartimento Matemat & Applicaz R Caccioppoli I-80126 Naples Italy Ist Nazl Fis Nucl Sez Napoli I-80126 Naples Italy Univ Salerno DMI I-84081 Baronissi SA Italy INFM Unita Salerno Salerno Italy Univ Naples Federico II Dipartimento Sci Fis I-80126 Naples Italy Univ Naples Federico II Dipartimento Endocrinol & Oncol Mol & Clin I-80126 Naples Italy

ISBN: (数字)9783540458081

ISBN: (纸本)3540442650

In this paper the fundamentals of Bayesian learning techniques are shown, and their application to neural network modeling is illustrated. Furthermore, it is shown how constraints on weight space can easily be embedded in a Bayesian framework. Finally, the application of these techniques to a complex neural network model for survival analysis is used as a significant example.

关键词： Bayesian learning frameworks learning with constraints survival analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：