Boolean kernels for rule based interpretation of support vector machines

Polato, Mirko; Aiolli, Fabio

doi:10.1016/j.neucom.2018.11.094

Cited by 10 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides its theoretical value, this kernels family hugely improves the interpretability of Boolean kernels as shown in [9], and achieves state-of-the-art performance on both classification tasks [26] and on top-N item recommendation tasks [27].…”

Section: Boolean Kernels For Categorical Datamentioning

confidence: 98%

“…In other words, these kernels compute the number of logical rules of a fixed form over the input variables that are satisfied in both the input vectors. To show that Boolean kernels can hugely improve the interpretability of SVM, in [9] a proof of concept method based on a genetic algorithm has been proposed. This algorithm can extract from the hypothesis of an SVM the most influential features (of the feature space) in the decision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Propositional Kernels

Polato

Aiolli

2021

Entropy

Self Cite

View full text Add to dashboard Cite

The pervasive presence of artificial intelligence (AI) in our everyday life has nourished the pursuit of explainable AI. Since the dawn of AI, logic has been widely used to express, in a human-friendly fashion, the internal process that led an (intelligent) system to deliver a specific output. In this paper, we take a step forward in this direction by introducing a novel family of kernels, called Propositional kernels, that construct feature spaces that are easy to interpret. Specifically, Propositional Kernel functions compute the similarity between two binary vectors in a feature space composed of logical propositions of a fixed form. The Propositional kernel framework improves upon the recent Boolean kernel framework by providing more expressive kernels. In addition to the theoretical definitions, we also provide an algorithm (and the source code) to efficiently construct any propositional kernel. An extensive empirical evaluation shows the effectiveness of Propositional kernels on several artificial and benchmark categorical data sets.

show abstract

Section: Boolean Kernels For Categorical Datamentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Propositional Kernels

Polato

Aiolli

2021

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Feature Coefficient Beyond the interpretations of simple algorithms, researchers have spent substantial efforts to develop model-specific interpretation approaches for models using complex models that are generally considered as not interpretable-by-nature, such as random forest (47), support vector machine (48), and neural networks (49, 50). Although these model-specific interpretation methods allow an easy understanding of model behaviors, the primary limitation is the limited flexibility of these methods.…”

Section: Nomentioning

confidence: 99%

On the importance of interpretable machine learning predictions to inform clinical decision making in oncology

Swisher

Chung

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

Machine learning-based tools are capable of guiding individualized clinical management and decision-making by providing predictions of a patient’s future health state. Through their ability to model complex nonlinear relationships, ML algorithms can often outperform traditional statistical prediction approaches, but the use of nonlinear functions can mean that ML techniques may also be less interpretable than traditional statistical methodologies. While there are benefits of intrinsic interpretability, many model-agnostic approaches now exist and can provide insight into the way in which ML systems make decisions. In this paper, we describe how different algorithms can be interpreted and introduce some techniques for interpreting complex nonlinear algorithms.

show abstract

“…The first trend is the rule-based post-explainability, where a group of researchers constructed them using the trained SVM models. For example, Polato and Aiolli (2019) introduced a method to obtain the explanation rules from the trained SVM model using boolean kernels with the feature spaces makeup of logical statements. Moreover, a searching strategy was implemented to extract the most important features/rules that efficiently explained the trained model.…”

Section: Support Vector Machinementioning

confidence: 99%

Explainable artificial intelligence: a comprehensive review

et al. 2021

View full text Add to dashboard Cite

Thanks to the exponential growth in computing power and vast amounts of data, artificial intelligence (AI) has witnessed remarkable developments in recent years, enabling it to be ubiquitously adopted in our daily lives. Even though AI-powered systems have brought competitive advantages, the black-box nature makes them lack transparency and prevents them from explaining their decisions. This issue has motivated the introduction of explainable artificial intelligence (XAI), which promotes AI algorithms that can show their internal process and explain how they made decisions. The number of XAI research has increased significantly in recent years, but there lacks a unified and comprehensive review of the latest XAI progress. This review aims to bridge the gap by discovering the critical perspectives of the rapidly growing body of research associated with XAI. After offering the readers a solid XAI background, we analyze and review various XAI methods, which are grouped into (i) pre-modeling explainability, (ii) interpretable model, and (iii) post-modeling explainability. We also pay attention to the current methods that dedicate to interpret and analyze deep learning methods. In addition, we systematically discuss various XAI challenges, such as the trade-off between the performance and the explainability, evaluation methods, security, and policy. Finally, we show the standard approaches that are leveraged to deal with the mentioned challenges.

show abstract

Boolean kernels for rule based interpretation of support vector machines

Cited by 10 publications

References 18 publications

Propositional Kernels

Propositional Kernels

On the importance of interpretable machine learning predictions to inform clinical decision making in oncology

Explainable artificial intelligence: a comprehensive review

Contact Info

Product

Resources

About