Simplifying decision trees
Reads0
Chats0
TLDR
Techniques for simplifying decision trees while retaining their accuracy are discussed, described, illustrated, and compared on a test-bed of decision trees from a variety of domains.Abstract:
Many systems have been developed for constructing decision trees from collections of examples. Although the decision trees generated by these methods are accurate and efficient, they often suffer the disadvantage of excessive complexity and are therefore incomprehensible to experts. It is questionable whether opaque structures of this kind can be described as knowledge, no matter how well they function. This paper discusses techniques for simplifying decision trees while retaining their accuracy. Four methods are described, illustrated, and compared on a test-bed of decision trees from a variety of domains.read more
Citations
More filters
Predicting Protein-Protein Interactions Using Relational Features
Louis Licamele,Lise Getoor +1 more
TL;DR: This work proposes several novel relational features for predicting protein-protein interaction that can be used in any classifier, and shows that it is able to get an accuracy of 81.7% when predicting new links from noisy high throughput data.
Journal ArticleDOI
A neural tree and its application to spam e-mail detection
TL;DR: A tree-structured neural network composed of neurons with quadratic neural-type junctions for pattern classification and the partial incremental capability so that it does not need to re-construct a new neural tree to accommodate new training data whenever new data are introduced to a trained QUANT.
Journal ArticleDOI
Rules Generation from the Decision Tree
TL;DR: An algorithm to remove irrelevant conditions of rules in the process of converting the decision tree to rules according to the semantics of the decisionTree can be integrated into any existing tree-construction algorithm with negligible increase in computational cost concerning that of constructing the decision Tree.
Journal ArticleDOI
Vertex and energy reconstruction in JUNO with machine learning methods
Zhen Qian,V. Belavin,Vasily Bokov,Vasily Bokov,R. Brugnera,Alessandro Compagnucci,Arsenii Gavrikov,Arsenii Gavrikov,A. Garfagnini,Maxim Gonchar,Leyla Khatbullina,Zi-Yuan Li,Wuming Luo,Yury Malyshkin,Samuele Piccinelli,Ivan Provilkov,Fedor Ratnikov,Dmitry Selivanov,K. Treskov,Andrey Ustyuzhanin,Francesco Vidaich,Z. Y. You,Yumei Zhang,Jiang Zhu,Francesco Manzali +24 more
TL;DR: In this paper, several machine learning approaches were compared and studied, including Boosted Decision Trees (BDT), deep neural networks (DNN), a few kinds of Convolution Neural Networks (CNN), based on ResNet and VGG, and a Graph Neural Network based on DeepSphere.
Proceedings ArticleDOI
Decision tree pruning using backpropagation neural networks
TL;DR: Backpropagation neural networks are used for pruning decision trees to give weights to nodes according to their significance, demonstrating that this method outperforms error-based pruning.
References
More filters
Journal ArticleDOI
Classification and Regression Trees.
Journal ArticleDOI
Induction of Decision Trees
TL;DR: In this paper, an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, is described, and a reported shortcoming of the basic algorithm is discussed.
Book
A Guide to Expert Systems
TL;DR: Technical managers, professionals, and researchers who are considering the implementation or application of expert systems will find this book to be an authoritative, but accessible guide to the state-of-the-art.
Book
Pattern-directed inference systems
TL;DR: In this paper, the authors discuss a crop identification and acreage estimation case study, followed by rather brief discussions of five selected management problems: large area land use inventory and forest, snow-cover, geologic, and water-temperature mapping.