Extracting Tree-Structured Representations of Trained Networks

Abstract

A significant limitation of neural networks is that the represen(cid:173) tations they learn are usually incomprehensible to humans. We present a novel algorithm , TREPAN, for extracting comprehensible, symbolic representations from trained neural networks. Our algo(cid:173) rithm uses queries to induce a decision tree that approximates the concept represented by a given network. Our experiments demon(cid:173) strate that TREPAN is able to produce decision trees that maintain a high level of fidelity to their respective networks while being com(cid:173) prehensible and accurate. Unlike previous work in this area, our algorithm is general in its applicability and scales well to large net(cid:173) works and problems with high-dimensional input spaces.

Cite

Text

Craven and Shavlik. "Extracting Tree-Structured Representations of Trained Networks." Neural Information Processing Systems, 1995.

Markdown

[Craven and Shavlik. "Extracting Tree-Structured Representations of Trained Networks." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/craven1995neurips-extracting/)

BibTeX

@inproceedings{craven1995neurips-extracting,
  title     = {{Extracting Tree-Structured Representations of Trained Networks}},
  author    = {Craven, Mark and Shavlik, Jude W.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {24-30},
  url       = {https://mlanthology.org/neurips/1995/craven1995neurips-extracting/}
}