EXTRACTION OF INTERPRETABLE DECISION RULES FROM BLACK-BOX MODELS FOR CLASSIFICATION TASKS

Download

Thesis.pdf

Date

2022-8-31

Author

GALATALI, EGEMEN BERK

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

227
views

150
downloads

In this work, we have proposed a new method and ready to use workflow to extract simplified rule sets for a given Machine Learning (ML) model trained on a classifi- cation task. Those rules are both human readable and in the form of software code pieces thanks to the syntax of Python programming language. We have inspired from the power of Shapley Values as our source of truth to select most prominent features for our rule sets. The aim of this work to select the key interval points in given data in order to extract if-then rule sets representing the black box models. We are able to generate rules that can mimic four different ML models on three datasets and one Deep Learning model on stock price dataset. We have evaluated promising similarity scores (around 90%) between the extracted rules and the ML models.

Subject Keywords

classification, machine learning, explainability, Interpretability, Deep learning

URI

https://hdl.handle.net/11511/99494

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Deep Learning-Based Hybrid Approach for Phase Retrieval IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24) We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
Out-of-Sample Generalizations for Supervised Manifold Learning for Classification Vural, Elif (2016-03-01) Supervised manifold learning methods for data classification map high-dimensional data samples to a lower dimensional domain in a structure-preserving way while increasing the separation between different classes. Most manifold learning methods compute the embedding only of the initially available data; however, the generalization of the embedding to novel points, i.e., the out-of-sample extension problem, becomes especially important in classification applications. In this paper, we propose a semi-supervis...
Feature Dimensionality Reduction with Variational Autoencoders in Deep Bayesian Active Learning Ertekin Bolelli, Şeyda (2021-06-09) Data annotation for training of supervised learning algorithms has been a very costly procedure. The aim of deep active learning methodologies is to acquire the highest performance in supervised deep learning models by annotating as few data points as possible. As the feature space of data grows, the application of linear models in active learning settings has become insufficient. Therefore, Deep Bayesian Active Learning methodology which represents model uncertainty has been widely studied. In this paper, ...
A Trie-structured Bayesian Model for Unsupervised Morphological Segmentation Kurfalı, Murathan; Ustun, Ahmet; CAN BUĞLALILAR, BURCU (2017-04-23) In this paper, we introduce a trie-structured Bayesian model for unsupervised morphological segmentation. We adopt prior information from different sources in the model. We use neural word embeddings to discover words that are morphologically derived from each other and thereby that are semantically similar. We use letter successor variety counts obtained from tries that are built by neural word embeddings. Our results show that using different information sources such as neural word embeddings and letter s...
A Bayesian Approach to Learning Scoring Systems Ertekin Bolelli, Şeyda (2015-12-01) We present a Bayesian method for building scoring systems, which are linear models with coefficients that have very few significant digits. Usually the construction of scoring systems involve manual efforthumans invent the full scoring system without using data, or they choose how logistic regression coefficients should be scaled and rounded to produce a scoring system. These kinds of heuristics lead to suboptimal solutions. Our approach is different in that humans need only specify the prior over what the ...

Citation Formats

E. B. GALATALI, “EXTRACTION OF INTERPRETABLE DECISION RULES FROM BLACK-BOX MODELS FOR CLASSIFICATION TASKS,” M.S. - Master of Science, Middle East Technical University, 2022.