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
View PDF on arXiv
7 Citations
Methods Citations
1

7 Citations

Citation Type

Citation Type

Rule Extraction from Training Data Using Neural Network
  • 14
Model Extraction Warning in MLaaS Paradigm
  • 50
  • PDF
Accuracy and Interpretability Trade-Offs in Machine Learning Applied to Safer Gambling
  • 14
  • PDF
Interpretability of Blackbox Machine Learning Models through Dataview Extraction and Shadow Model creation
  • PDF
The Need for Knowledge Extraction: Understanding Harmful Gambling Behavior with Neural Networks
  • 7
  • PDF
Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262
  • 34
  • PDF
Design of efficient computational workflows for in silico drug repurposing.
  • 67
  • PDF

References

SHOWING 1-10 OF 45 REFERENCES
Extracting comprehensible models from trained neural networks
  • 248
  • PDF
Survey and critique of techniques for extracting rules from trained artificial neural networks
  • 1,165
Extracting Tree-Structured Representations of Trained Networks
  • 537
Using Neural Network Rule Extraction and Decision Tables for Credit - Risk Evaluation
  • 333
  • PDF
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks
  • 432
Extracting Rules from Artifical Neural Networks with Distributed Representations
  • 194
  • PDF
Using Sampling and Queries to Extract Rules from Trained Neural Networks
  • 320
Comparison Between Artificial Neural Network Learning Algorithms For Prediction Of Student Average Considering Effective Factors In Learning And Educational Progress
  • 8
Classification and regression trees
  • W. Loh
  • Computer Science
  • Wiley Interdiscip. Rev. Data Min. Knowl. Discov.
  • 2011
  • 14,856
  • PDF
Extracting refined rules from knowledge-based neural networks
  • 147
  • PDF
...
1
2
3
4
5
...