X-TREPAN: a multi class regression and adapted extraction of comprehensible decision tree in artificial neural networks
@article{Awudu2015XTREPANAM, title={X-TREPAN: a multi class regression and adapted extraction of comprehensible decision tree in artificial neural networks}, author={Karim Awudu and S. Zhou}, journal={ArXiv}, year={2015}, volume={abs/1508.07551} }
In this work, the TREPAN algorithm is enhanced and extended for extracting decision trees from neural networks. [...] Key Method This benchmark enhancement was achieved by adapting Single-test TREPAN and C4.5 decision tree induction algorithms to analyze the datasets. The models are then compared with X-TREPAN for comprehensibility and classification accuracy. Furthermore, we validate the experimentations by applying statistical methods. Finally, the modified algorithm is extended to work with multi-class…Expand
Figures, Tables, and Topics from this paper
7 Citations
Rule Extraction from Training Data Using Neural Network
- Computer Science
- Int. J. Artif. Intell. Tools
- 2017
- 14
Accuracy and Interpretability Trade-Offs in Machine Learning Applied to Safer Gambling
- Computer Science
- CoCo@NIPS
- 2016
- 13
- PDF
Interpretability of Blackbox Machine Learning Models through Dataview Extraction and Shadow Model creation
- Computer Science, Mathematics
- ArXiv
- 2020
- PDF
The Need for Knowledge Extraction: Understanding Harmful Gambling Behavior with Neural Networks
- Computer Science
- ECAI
- 2016
- 7
- PDF
Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262
- Mathematics, Computer Science
- ArXiv
- 2018
- 32
- PDF
Design of efficient computational workflows for in silico drug repurposing.
- Computer Science, Medicine
- Drug discovery today
- 2017
- 66
- PDF
References
SHOWING 1-10 OF 45 REFERENCES
Survey and critique of techniques for extracting rules from trained artificial neural networks
- Computer Science
- Knowl. Based Syst.
- 1995
- 1,161
Using Neural Network Rule Extraction and Decision Tables for Credit - Risk Evaluation
- Computer Science
- Manag. Sci.
- 2003
- 326
- PDF
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks
- Computer Science, Medicine
- IEEE Trans. Neural Networks
- 1998
- 430
Extracting Rules from Artifical Neural Networks with Distributed Representations
- Computer Science
- NIPS
- 1994
- 193
- PDF
Comparison Between Artificial Neural Network Learning Algorithms For Prediction Of Student Average Considering Effective Factors In Learning And Educational Progress
- Computer Science
- 2014
- 8
Classification and regression trees
- Computer Science
- Wiley Interdiscip. Rev. Data Min. Knowl. Discov.
- 2011
- 14,617
- PDF
Extracting refined rules from knowledge-based neural networks
- Computer Science
- Machine Learning
- 2004
- 145
- PDF