检索结果-内蒙古大学图书馆

36th International Conference on logic programming (ICLP)

作者： Shakerin, Farhad Gupta, Gopal Univ Texas Dallas Richardson TX 75083 USA

We focus on the problem of inducing logic programs that explain models learned by the support vector machine (SVM) algorithm. The top-down sequential covering inductive logic programming (ILP) algorithms (e.g., FOIL) apply hill-climbing search using heuristics from information theory. A major issue with this class of algorithms is getting stuck in local optima. In our new approach, however, the data-dependent hill-climbing search is replaced with a model-dependent search where a globally optimal SVM model is trained first, then the algorithm looks into support vectors as the most influential data points in the model, and induces a clause that would cover the support vector and points that are most similar to that support vector. Instead of defining a fixed hypothesis search space, our algorithm makes use of SHAP, an example-specific interpreter in explainable AI, to determine a relevant set of features. This approach yields an algorithm that captures the SVM model's underlying logic and outperforms other ILP algorithms in terms of the number of induced clauses and classification evaluation metrics.

关键词： Explainable AI Data Mining inductive logic programming Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Enriching Visual with Verbal Explanations for Relational Concepts - Combining LIME with Aleph 19th

Enriching Visual with Verbal Explanations for Relational Con...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Rabold, Johannes Deininger, Hannah Siebers, Michael Schmid, Ute Univ Bamberg Cognit Syst Bamberg Germany

ISBN: (纸本)9783030438234;9783030438227

With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier's decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the eye is wide open). Furthermore, highlighting cannot convey whether the classification depends on the mere presence of parts or on a specific spatial relation between them. Consequently, we present an approach that is capable of explaining a classifier's decision in terms of logic rules obtained by the inductive logic programming system Aleph. The examples and the background knowledge needed for Aleph are based on the explanation generation method LIME. We demonstrate our approach with images of a blocksworld domain. First, we show that our approach is capable of identifying a single relation as important explanatory construct. Afterwards, we present the more complex relational concept of towers. Finally, we show how the generated relational rules can be explicitly related with the input image, resulting in richer explanations.

关键词： XAI Deep learning inductive logic programming

来源：评论

学校读者我要写书评

暂无评论

Expressive Explanations of DNNs by Combining Concept Analysis with ILP 43rd

Expressive Explanations of DNNs by Combining Concept Analysi...

引用

43rd German Conference on Artificial Intelligence (KI)

作者： Rabold, Johannes Schwalbe, Gesina Schmid, Ute Univ Bamberg Cognit Syst Bamberg Germany Continental AG Artificial Intelligence Holist Engn & Technol Regensburg Germany

ISBN: (纸本)9783030582845;9783030582852

Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assistant systems, and applications concerned with the General Data Protection Regulation of the European Union, which features transparency as a cornerstone. Such demands require the ability to audit the rationale behind a classifier's decision. While visualizations are the de facto standard of explanations, they come short in terms of expressiveness in many ways: They cannot distinguish between different attribute manifestations of visual features (e.g. eye open vs. closed), and they cannot accurately describe the influence of absence of, and relations between features. An alternative would be more expressive symbolic surrogate models. However, these require symbolic inputs, which are not readily available in most computer vision tasks. In this paper we investigate how to overcome this: We use inherent features learned by the network to build a global, expressive, verbal explanation of the rationale of a feed-forward convolutional deep neural network (DNN). The semantics of the features are mined by a concept analysis approach trained on a set of human understandable visual concepts. The explanation is found by an inductive logic programming (ILP) method and presented as first-order rules. We show that our explanation is faithful to the original black-box model (The code for our experiments is available at https://***/mc-lovin-mlem/concept-embeddings-and-ilp/tree/ki2020).

关键词： Explainable AI Concept analysis Concept embeddings inductive logic programming

来源：评论

学校读者我要写书评

暂无评论

Whitebox Induction of Default Rules Using High-Utility Itemset Mining 22nd

Whitebox Induction of Default Rules Using High-Utility Items...

引用

22nd International Symposium on Practical Aspects of Declarative Languages (PADL)

作者： Shakerin, Farhad Gupta, Gopal Univ Texas Dallas Richardson TX 75080 USA

ISBN: (纸本)9783030391973;9783030391966

We present a fast and scalable algorithm to induce non-monotonic logic programs from statistical learning models. We reduce the problem of search for best clauses to instances of the High-Utility Itemset Mining (HUIM) problem. In the HUIM problem, feature values and their importance are treated as transactions and utilities respectively. We make use of TreeExplainer, a fast and scalable implementation of the Explainable AI tool SHAP, to extract locally important features and their weights from ensemble tree models. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics and training time compared to ALEPH, a state-of-the-art inductive logic programming (ILP) system.

关键词： inductive logic programming Machine learning Explainable AI Negation as failure Answer set programming Data mining

来源：评论

学校读者我要写书评

暂无评论

CONNER: A Concurrent ILP Learner in Description logic 1

引用

29th International Conference on inductive logic programming

作者： Algahtani, Eyad Kazakov, Dimitar Univ York York YO10 5GH N Yorkshire England

ISBN: (数字)9783030492106

ISBN: (纸本)9783030492090;9783030492106

Machine Learning (ML) approaches can achieve impressive results, but many lack transparency or have difficulties handling data of high structural complexity. The class of ML known as inductive logic programming (ILP) draws on the expressivity and rigour of subsets of First Order logic to represent both data and models. When Description logics (DL) are used, the approach can be applied directly to knowledge represented as ontologies. ILP output is a prime candidate for explainable artificial intelligence;the expense being computational complexity. We have recently demonstrated how a critical component of ILP learners in DL, namely, cover set testing, can be speeded up through the use of concurrent processing. Here we describe the first prototype of an ILP learner in DL that benefits from this use of concurrency. The result is a fast, scalable tool that can be applied directly to large ontologies.

关键词： inductive logic programming Description logics Ontologies Parallel computing GPGPU

来源：评论

学校读者我要写书评

暂无评论

Efficient program synthesis using constraint satisfaction in inductive logic programming

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2013年第1期14卷

作者： Kevin Murphy Bernhard Schölkopf John Ahlgren Shiu Yin Yuen Google MPI for Intelligent Systems Department of Electronic Engineering City University of Hong Kong Hong Kong China

We present NrSample, a framework for program synthesis in inductive logic programming. NrSample uses propositional logic constraints to exclude undesirable candidates from the search. This is achieved by representing constraints as propositional formulae and solving the associated constraint satisfaction problem. We present a variety of such constraints: pruning, input-output, functional (arithmetic), and variable splitting. NrSample is also capable of detecting search space exhaustion, leading to further speedups in clause induction and optimality. We benchmark NrSample against enumeration search (Aleph's default) and Progol's A* search in the context of program synthesis. The results show that, on large program synthesis problems, NrSample induces between 1 and 1358 times faster than enumeration (236 times faster on average), always with similar or better accuracy. Compared to Progol A*, NrSample is 18 times faster on average with similar or better accuracy except for two problems: one in which Progol A* substantially sacrificed accuracy to induce faster, and one in which Progol A* was a clear winner. Functional constraints provide a speedup of up to 53 times (21 times on average) with similar or better accuracy. We also benchmark using a few concept learning (non-program synthesis) problems. The results indicate that without strong constraints, the overhead of solving constraints is not compensated for.

关键词： Boolean satisfiability problem constraint satisfaction inductive logic programming program synthesis theory induction

来源：评论

学校读者我要写书评

暂无评论

From Fifth Generation Computing to Skill Science: A Biographical Essay of Koichi Furukawa

引用

NEW GENERATION COMPUTING 2019年第2期37卷 141-158页

作者： Ozaki, Tomonobu Goebel, Randy Inoue, Katsumi Nihon Univ Coll Humanities & Sci Tokyo Japan Univ Alberta Dept Comp Sci Edmonton AB Canada Natl Inst Informat Tokyo Japan Grad Univ Adv Studies SOKENDAI Dept Informat Tokyo Japan Tokyo Inst Technol Sch Comp Dept Comp Sci Tokyo Japan

Professor Koichi Furukawa, an eminent computer scientist and former Editor-in-Chief of the New Generation Computing journal, passed away on January 31, 2017. His passing was a surprise, and we were all shocked and saddened by the news. To remember the deceased, this article reviews the great career and contributions of Professor Koichi Furukawa, focusing on his research activities on the foundation and application of logic programming. Professor Furukawa had both a deep understanding and broad impact on logic programming, and he was always gentle but persistent in articulating its value across a broad spectrum of computer science and artificial intelligence research. This article introduces his research along with its insightful and unique philosophical framework.

关键词： Institute for New Generation Computer Technology logic programming inductive logic programming Skill science

来源：评论

学校读者我要写书评

暂无评论

logical Explanations for Deep Relational Machines Using Relevance Information

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2019年第1期20卷 1-47页

作者： Srinivasan, Ashwin Vig, Lovekesh Bain, Michael BITS Pilani Dept Comp Sc & Informat Syst KK Birla Goa Campus Zuari Nagar Goa India TCS Res New Delhi India Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia

Our interest in this paper is in the construction of symbolic explanations for predictions made by a deep neural network. We will focus attention on deep relational machines (DRMs: a term introduced in Lodhi (2013)). A DRM is a deep network in which the input layer consists of Boolean-valued functions (features) that are defined in terms of relations provided as domain, or background, knowledge. Our DRMs differ from those in Lodhi (2013), which uses an inductive logic programming (ILP) engine to first select features (we use random selections from a space of features that satisfies some approximate constraints on logical relevance and non-redundancy). But why do the DRMs predict what they do? One way of answering this was provided in recent work Ribeiro et al. (2016), by constructing readable proxies for a black-box predictor. The proxies are intended only to model the predictions of the black-box in local regions of the instance-space. But readability alone may not be enough: to be understandable, the local models must use relevant concepts in an meaningful manner. We investigate the use of a Bayes-like approach to identify logical proxies for local predictions of a DRM. As a preliminary step, we show that DRM's with our randomised propositionalization method achieve predictive performance that is comparable to the best reports in the ILP literature. Our principal results on logical explanations show: (a) Models in first-order logic can approximate the DRM's prediction closely in a small local region;and (b) Expert-provided relevance information can play the role of a prior to distinguish between logical explanations that perform equivalently on prediction alone.

关键词： Explainable AI inductive logic programming Deep Relational Machines

来源：评论

学校读者我要写书评

暂无评论

Inducing Rules about Distributed Robotic Systems for Fault Detection & Diagnosis 21

Inducing Rules about Distributed Robotic Systems for Fault D...

引用

Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems

作者： Youssef Mahmoud Youssef Hochschule Bonn-Rhein-Sieg Bonn Germany

ISBN: (纸本)9781450383073

This paper presents an extended abstract for the PhD topic Inducing Rules about Distributed Robotic Systems for Fault Detection & Diagnosis. The research focuses on developing novel methods for fault detection and diagnosis using explainable machine learning. The main field of application is distributed robotic systems. With current developments in distributed robot technology, the problem of detecting and diagnosing faults becomes more complex.

关键词： robotics explainable machine learning inductive logic programming fault detection & diagnosis

来源：评论

学校读者我要写书评

暂无评论

Online probabilistic theory revision from examples with ProPPR

引用

MACHINE LEARNING 2019年第7期108卷 1165-1189页

作者： Guimaraes, Victor Paes, Aline Zaverucha, Gerson Univ Fed Rio de Janeiro COPPE Dept Syst Engn & Comp Sci Rio de Janeiro RJ Brazil Univ Fed Fluminense Dept Comp Sci Niteroi RJ Brazil

Handling relational data streams has become a crucial task, given the availability of pervasive sensors and Internet-produced content, such as social networks and knowledge graphs. In a relational environment, this is a particularly challenging task, since one cannot assure that the streams of examples are independent along the iterations. Thus, most relational learning systems are still designed to learn only from closed batches of data. Furthermore, in case there is a previously acquired model, these systems either would discard it or assuming it as correct. In this work, we propose an online relational learning algorithm that can handle continuous, open-ended streams of relational examples as they arrive. We employ techniques of theory revision to take advantage of the previously acquired model as a starting point, by finding where it should be modified to cope with the new examples, and automatically update it. We rely on the Hoeffding's bound statistical theory to decide if the model must, in fact, be updated in accordance with the new examples. The proposed algorithm is built upon ProPPR statistical relational language, aiming at contemplating the uncertainty inherent to real data. Experimental results in social networks and entity co-reference datasets show the potential of the proposed approach compared to other relational learners.

关键词： Online learning Statistical relational learning Theory revision from examples inductive logic programming Mining data streams

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：