C4.5: Programs for Machine Learning (書評)

By 金田重郎. 1995

How researchers see this paper

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

Citations in the corpus

Please Stop Explaining Black Box Models for High Stakes Decisions (2018, background): “…or uninterpretable because they do not choose a globally best choice (or approximately best choice) for the logical conditions [C4.5 and CART decision trees are an example, Quinlan, 1993, Breiman et al., 1984, as well as a vast number of models from the associative classiﬁcation literature].”
Random forest classifier for remote sensing classification (2005, methodology): “The most frequently used attribute selection measures in decision tree induction are the Information Gain Ratio criterion (Quinlan 1993) and the Gini Index (Breiman et al. 1984).”
YaDT: yet another decision tree builder (2004, methodology): “At each node, theinformation gain[10] of each attribute is calculated with respect to the cases at the node.”
/*icomment: bugs or bad comments?*/ (2007, methodology): “5 Revision 8 [34], implemented in the software package”
A data mining approach to strategy prediction (2009, methodology): “The following algorithms were applied to classiﬁcation: • J48 – C4.5 decision tree [18] • k-NN – Nearest neighbor [19] • NNge – Non-nested generalized exemplars [20] • LogitBoost – Additive logistic regression [21] We used the implementations of these algorithms provided in the Weka [22] toolkit.”
Content-based book recommending using learning for text categorization (1999, background): “In particular, although naive Bayes is known to perform quite well on text categorization tasks, it will b e useful to compare it to other learning algorithms such as decision tree induction [38], rule induction [10], neural net work learning [44, 32], vector-space methods from information r etrieva”