REVISTA
AI

   
Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  AI  /  Vol: 4 Par: 2 (2023)  /  Artículo
ARTÍCULO
TITULO

An Empirical Comparison of Interpretable Models to Post-Hoc Explanations

Parisa Mahya and Johannes Fürnkranz    

Resumen

Recently, some effort went into explaining intransparent and black-box models, such as deep neural networks or random forests. So-called model-agnostic methods typically approximate the prediction of the intransparent black-box model with an interpretable model, without considering any specifics of the black-box model itself. It is a valid question whether direct learning of interpretable white-box models should not be preferred over post-hoc approximations of intransparent and black-box models. In this paper, we report the results of an empirical study, which compares post-hoc explanations and interpretable models on several datasets for rule-based and feature-based interpretable models. The results seem to underline that often directly learned interpretable models approximate the black-box models at least as well as their post-hoc surrogates, even though the former do not have direct access to the black-box model.

 Artículos similares

       
 
Hannes Zöschg    
Trash racks installed at hydropower plants cause head losses that reduce energy output. Previous research has thoroughly investigated head losses through both experimental and field studies. However, only a limited number of numerical studies have been p... ver más
Revista: Water

 
Shanshan Chen, Sheng Guan, Hui Wang, Ningqi Ye and Zexun Wei    
Ship type identification is an important basis for ship management and monitoring. The paper proposed a new method of ship type identification by combining characteristic parameters from the energy difference between high and low frequencies and the sens... ver más

 
Vadim Palchikovskiy, Aleksandr Kuznetsov, Igor Khramtsov and Oleg Kustov    
A comparison is considered of the experimentally obtained impedance of locally reacting acoustic liner samples with the impedance calculated using semi-empirical Goodrich, Sobolev and Eversman models. The semi-empirical impedance models are outlined. In ... ver más
Revista: Acoustics

 
Yulong Bai, Guolian Li, Tianxiu Lu, Yadong Wu, Weihan Zhang and Yidan Feng    
Most existing road network matching algorithms are designed based on previous rules and do not fully utilize the potential of big data and historical tracks. To solve this problem, we introduce a new road network matching algorithm based on deep learning... ver más
Revista: Applied Sciences

 
Fotios Bosmos, Alexandros T. Tzallas, Markos G. Tsipouras, Evripidis Glavas and Nikolaos Giannakeas    
The aim of this work is to highlight the possibilities of using VR applications in the informal learning process. This is attempted through the development of virtual reality cultural applications for historical monuments. For this purpose, the theoretic... ver más
Revista: Information