Prolog-based agnostic explanation module for structured pattern classification

12/23/2021
by   Gonzalo Nápoles, et al.
2

This paper presents a Prolog-based reasoning module to generate counterfactual explanations given the predictions computed by a black-box classifier. The proposed symbolic reasoning module can also resolve what-if queries using the ground-truth labels instead of the predicted ones. Overall, our approach comprises four well-defined stages that can be applied to any structured pattern classification problem. Firstly, we pre-process the given dataset by imputing missing values and normalizing the numerical features. Secondly, we transform numerical features into symbolic ones using fuzzy clustering such that extracted fuzzy clusters are mapped to an ordered set of predefined symbols. Thirdly, we encode instances as a Prolog rule using the nominal values, the predefined symbols, the decision classes, and the confidence values. Fourthly, we compute the overall confidence of each Prolog rule using fuzzy-rough set theory to handle the uncertainty caused by transforming numerical quantities into symbols. This step comes with an additional theoretical contribution to a new similarity function to compare the previously defined Prolog rules involving confidence values. Finally, we implement a chatbot as a proxy between human beings and the Prolog-based reasoning module to resolve natural language queries and generate counterfactual explanations. During the numerical simulations using synthetic datasets, we study the performance of our system when using different fuzzy operators and similarity functions. Towards the end, we illustrate how our reasoning module works using different use cases.

READ FULL TEXT

page 33

page 34

page 37

page 38

page 39

page 40

09/07/2018

Reductive property of new fuzzy reasoning method based on distance measure

Firstly in this paper we propose a new criterion function for evaluation...
01/03/2020

Modeling Uncertainty and Imprecision in Nonmonotonic Reasoning using Fuzzy Numbers

To deal with uncertainty in reasoning, interval-valued logic has been de...
10/19/2012

Dealing with uncertainty in fuzzy inductive reasoning methodology

The aim of this research is to develop a reasoning under uncertainty str...
04/28/2020

An ASP-Based Approach to Counterfactual Explanations for Classification

We propose answer-set programs that specify and compute counterfactual i...
07/05/2022

Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models

Explanations for black-box models help us understand model decisions as ...
08/01/2009

Knowledge Discovery of Hydrocyclone s Circuit Based on SONFIS and SORST

This study describes application of some approximate reasoning methods t...