Abstract
In this editorial, Guest Editors Richard Benjamins (Telefónica), Jeanine Vos (GSMA), and Stefaan Verhulst (
Data & Policy
Editor-in-Chief) draw insights from a set of peer-reviewed, open ...access articles in a
Data & Policy
special collection dedicated to the use of Telco Big Data Analytics for COVID-19.
OneClass SVM is a popular method for unsupervised anomaly detection. As many other methods, it suffers from the black box problem: it is difficult to justify, in an intuitive and simple manner, why ...the decision frontier is identifying data points as anomalous or non anomalous. This problem is being widely addressed for supervised models. However, it is still an uncharted area for unsupervised learning. In this paper, we evaluate several rule extraction techniques over OneClass SVM models, while presenting alternative designs for some of those algorithms. Furthermore, we propose algorithms for computing metrics related to eXplainable Artificial Intelligence (XAI) regarding the “comprehensibility”, “representativeness”, “stability” and “diversity” of the extracted rules. We evaluate our proposals with different data sets, including real-world data coming from industry. Consequently, our proposal contributes to extending XAI techniques to unsupervised machine learning models.
•Rule extraction for unsupervised outlier detection models using OCSVM.•Design and evaluate alternatives over rule extraction algorithms.•XAI metric evaluation: comprehensibility, representativeness, stability and diversity.•Quantify quality of the explanations with XAI metrics for P@1 rules.•Measure the kernel influence in the number of rules generated.
In this contribution to the special issue of the International Journal of Human-Computer Studies on Knowledge Acquisition I will give a view on the evolution of concepts related to knowledge during ...the last 25 years and will briefly look into the future. The concepts include knowledge acquisition, knowledge engineering, knowledge management, knowledge level, knowledge retrieval, knowledge modeling, knowledge protection, knowledge retention, knowledge deletion and knowledge privacy. This contribution is a reflection on the theme Knowledge Acquisition based on my experience from 1987 when I started working in this area.
•We review concepts related to the explainability of AI methods (XAI).•We comprehensive analyze the XAI literature organized in two taxonomies.•We identify future research directions of the XAI ...field.•We discuss potential implications of XAI and privacy in data fusion contexts.•We identify Responsible AI as a concept promoting XAI and other AI principles in practical settings.
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
OneClass SVM is a popular method for unsupervised anomaly detection. As many other methods, it suffers from the black box problem: it is difficult to justify, in an intuitive and simple manner, why ...the decision frontier is identifying data points as anomalous or non anomalous. This problem is being widely addressed for supervised models. However, it is still an uncharted area for unsupervised learning. In this paper, we evaluate several rule extraction techniques over OneClass SVM models, while presenting alternative designs for some of those algorithms. Furthermore, we propose algorithms for computing metrics related to eXplainable Artificial Intelligence (XAI) regarding the "comprehensibility", "representativeness", "stability" and "diversity" of the extracted rules. We evaluate our proposals with different data sets, including real-world data coming from industry. Consequently, our proposal contributes to extending XAI techniques to unsupervised machine learning models.
The Semantic Web - ISWC 2005 Gil, Yolanda; Motta, Enrico; Benjamins, V. Richard ...
2005, 2005-12-15, Letnik:
3729
eBook
This book constitutes the refereed proceedings of the 4th International Semantic Web Conference, ISWC 2005, held in Galway, Ireland, in November 2005.
The 54 revised full academic papers and 17 ...revised industrial papers presented together with abstracts of 3 invited talks were carefully reviewed and selected from a total of 217 submitted papers to the academic track and 30 to the industrial track. The research papers address all current issues in the field of the semantic Web, ranging from theoretical aspects to various applications. The industrial track contains papers on applications in particular industrical sectors, new technology for building applications, and methodological and feasibility aspects of building industrical applications that incorporate semantic Web technology. Short descriptions of the top five winning applications submitted to the Semantic Web Challenge competition conclude the volume.
Tor the past few years, the Semantic Web has been enjoying significant investment, mostly through research but to a lesser extent through start-ups and commercial projects. A major topic of ...discussion is where we can see those investments' results, so I asked several experts to consider what semantic technology will accomplish in the near future. The experts are from academia, venture capitalist firms, and companies focused on semantic technology, telecommunication, and Web 2.0.