Clustering-Based Approaches for Symbolic Knowledge Extraction

11/01/2022
by   Federico Sabbatini, et al.
0

Opaque models belonging to the machine learning world are ever more exploited in the most different application areas. These models, acting as black boxes (BB) from the human perspective, cannot be entirely trusted if the application is critical unless there exists a method to extract symbolic and human-readable knowledge out of them. In this paper we analyse a recurrent design adopted by symbolic knowledge extractors for BB regressors - that is, the creation of rules associated with hypercubic input space regions. We argue that this kind of partitioning may lead to suboptimal solutions when the data set at hand is high-dimensional or does not satisfy symmetric constraints. We then propose a (deep) clustering-based approach to be performed before symbolic knowledge extraction to achieve better performance with data sets of any kind.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/01/2022

Evaluation Metrics for Symbolic Knowledge Extracted from Machine Learning Black Boxes: A Discussion Paper

As opaque decision systems are being increasingly adopted in almost any ...
research
09/10/2022

Symbolic Knowledge Extraction from Opaque Predictors Applied to Cosmic-Ray Data Gathered with LISA Pathfinder

Machine learning models are nowadays ubiquitous in space missions, perfo...
research
12/12/2019

The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)

Lample and Charton (2019) describe a system that uses deep learning tech...
research
07/04/2020

Neuro-Symbolic Generative Art: A Preliminary Study

There are two classes of generative art approaches: neural, where a deep...
research
04/11/2016

Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks

This work describes a methodology to combine logic-based systems and con...
research
11/07/2019

Can Neural Networks Learn Symbolic Rewriting?

This work investigates if the current neural architectures are adequate ...
research
04/04/2021

A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

Event coreference resolution is an important research problem with many ...

Please sign up or login with your details

Forgot password? Click here to reset