Seeing the Forest Through the Trees

By Anneleen Van Assche, Hendrik Blockeel. 2007

79 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Interpretability via Model Extraction (2017, methodology): “Previous model extraction approaches have focused on specific model families [10, 28, 29], enabling them to leverage the internal structure of the model.”
Interpreting Blackbox Models via Model Extraction (2017, neutral): “Previous model extraction approaches have focused on interpreting speciﬁc families of models such as random forests [45, 18, 46], enabling them to leverage domain-speciﬁc knowledge about the internal structure of the model.”
Software Vulnerability Analysis and Discovery Using Machine-Learning and Data-Mining Techniques (2017, result): “, Walden et al. (2014)) that show basic text mining on software source code can yield better results in terms of prediction performace compared to vulnerability prediction models based on some software metrics; although, this empirical study can’t be generalized to all software projects and all soft”
Principles and Practice of Explainable Machine Learning (2020, methodology): “• Other approaches, similar in spirit, can be found in [84, 90], where the objective is to approximate the RF using a single decision tree.”
A Genetic Algorithm for Interpretable Model Extraction from Decision Tree Ensembles (2017, methodology): “[8], a technique called Interpretable Single Model (ism) is proposed.”
Comprehensible classification models: a position paper (2014, background): “Indeed, the models produced by SVMs are in general black box models that can be hardly interpreted by users; whilst an ensemble of models tends to be harder to be interpreted by users, by comparison with a single classification model [23], [26], [69].”