Usporedite metode

	Objašnjivi potporni vektorski stroj	Objašnjivi Naivni Bayes
Područje	Strojno učenje	Strojno učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2016–2017 (XAI layer)	1950s (Naive Bayes); 2000s–2010s (explainability focus)
Tvorac	Cortes & Vapnik (SVM); explainability layer via Lundberg & Lee (SHAP, 2017) and Ribeiro et al. (LIME, 2016)	Zhang, H. (explainability framing); Naive Bayes: Good, I. J.
Vrsta	Post-hoc explainability applied to SVM	Probabilistic generative classifier with intrinsic explainability
Temeljni izvor	Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.	Rish, I. (2001). An empirical study of the naive Bayes classifier. In IJCAI Workshop on Empirical Methods in AI (pp. 41–46).
Drugi nazivi	Explainable SVM, Interpretable SVM, XAI-SVM, Transparent Support Vector Machine	XNB, interpretable Naive Bayes, transparent Naive Bayes, explainable probabilistic classifier
Srodne	4	4
Sažetak	Explainable SVM combines a trained Support Vector Machine with a post-hoc interpretability layer — typically SHAP or LIME — to produce feature-level explanations for individual predictions and global importance rankings. It retains the discriminative power of SVM while meeting transparency requirements in high-stakes domains such as medicine, finance, and law.	Explainable Naive Bayes extends the classic probabilistic Naive Bayes classifier with transparent, human-readable explanations of its predictions. By surfacing class priors, per-feature likelihoods, and log-odds contributions, it offers the interpretability demanded in high-stakes domains such as medicine, law, and education without sacrificing the simplicity and speed that make Naive Bayes a reliable baseline.