ITER: An Algorithm for Predictive Regression Rule Extraction

Huysmans, Johan; Baesens, Bart; Vanthienen, Jan

doi:10.1007/11823728_26

Cited by 27 publications

(28 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huysmans et al devised a pedagogical algorithm ITER for regression rule extraction [11]. ITER can extract regression rules from a trained black box model.…”

Section: Background and Literature Review Of Rule Extraction Frommentioning

confidence: 99%

KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction

Sethi¹,

Mishra

2012

2012 Third International Conference on Intelligent Systems Modelling and Simulation

View full text Add to dashboard Cite

Knowledge representation opaque model like ANN has advantage of accuracy and limitation of interpretability. Transparent models like decision tree, decision table and rules represent knowledge in more understandable form and can easily be integrated with other learning system. Converting an opaque model like ANN to transparent model is called rule extraction. Lot of work has been done in the field of rule extraction like "SVM to Rules", "ANN to Decision Tree", "ANN to Rules" etc. We did not find any direct approach of converting ANN to decision table in our literature survey. In this paper, we proposed a novel pedagogical rule extraction technique to generate a decision table using training example set and a trained artificial neural network on it. The proposed algorithm can be used with both discrete as well as continuous input. The proposed algorithm has advantage in terms of computational performance and memory management.

show abstract

“…Huysmans et al devised a pedagogical algorithm ITER for regression rule extraction [11]. ITER can extract regression rules from a trained black box model.…”

Section: Background and Literature Review Of Rule Extraction Frommentioning

confidence: 99%

KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction

Sethi¹,

Mishra

2012

2012 Third International Conference on Intelligent Systems Modelling and Simulation

View full text Add to dashboard Cite

show abstract

“…TREPAN (Craven and Shavlik 1995) is a successful pedagogical algorithm that learns decision trees from neural networks. Minerva and Iter (Huysmans et al 2006) are pedagogical approaches to extract rules from SVM models. There is also a broader pedagogical approach to rule extraction where an SVM model is trained first, then the entire training data is re-labeled using the predictions of the SVM model, and finally a rule learning method (e.g., C4.5, ID3, CART etc.)…”

Section: Related Workmentioning

confidence: 99%

“…Explaining the behavior of black-box models has motivated a long line of research in Rule Induction from SVM models. As we argue in more detail in section 5, all proposed Rule Extraction techniques either treat the model as a black-box Huysmans et al 2006), or are limited to certain type of kernels (Fung et al 2005), or are too complex to interpret (Nuñez et al 2002). A survey of existing Rule Extraction techniques can be found elsewhere (Diederich 2008).…”

Section: Introductionmentioning

confidence: 99%

White-box Induction From SVM Models: Explainable AI with Logic Programming

Shakerin¹,

Gupta²

2020

Theory and Practice of Logic Programming

View full text Add to dashboard Cite

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.

show abstract

“…If a continuous anomaly score is required to rank anomalies, we should then resort to regression rule extraction methods which learn rules producing a continuous output, e.g. REFANN [44], ITER [23] or classification and regression trees (cart) [3]. Both regression and classification rule mining methods show good performance when applied to numerical or one-hot encoded input data.…”

Section: Interpretabilitymentioning

confidence: 99%

A comparative evaluation of novelty detection algorithms for discrete sequences

et al. 2019

View full text Add to dashboard Cite

The identification of anomalies in temporal data is a core component of numerous research areas such as intrusion detection, fault prevention, genomics and fraud detection. This article provides an experimental comparison of the novelty detection problem applied to discrete sequences. The objective of this study is to identify which state-of-the-art methods are efficient and appropriate candidates for a given use case. These recommendations rely on extensive novelty detection experiments based on a variety of public datasets in addition to novel industrial datasets. We also perform thorough scalability and memory usage tests resulting in new supplementary insights of the methods' performance, key selection criterion to solve problems relying on large volumes of data and to meet the expectations of applications subject to strict response time constraints.

show abstract

ITER: An Algorithm for Predictive Regression Rule Extraction

Cited by 27 publications

References 5 publications

KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction

KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction

White-box Induction From SVM Models: Explainable AI with Logic Programming

A comparative evaluation of novelty detection algorithms for discrete sequences

Contact Info

Product

Resources

About