Looking Through Glass Box

TL;DR

This paper presents a neural network implementation of fuzzy cognitive maps that learns causality patterns, uses Langevin dynamics to avoid overfitting, and is evaluated on multiple datasets for performance.

Contribution

It introduces a neural network model for fuzzy cognitive maps with Langevin dynamics and provides an evaluation framework for its effectiveness.

Findings

Effective causality pattern learning demonstrated

Langevin dynamics help prevent overfitting

Network performs well on multiple datasets

Abstract

This essay is about a neural implementation of the fuzzy cognitive map, the FHM, and corresponding evaluations. Firstly, a neural net has been designed to behave the same way that an FCM does; as inputs it accepts many fuzzy cognitive maps and propagates them in order to learn causality patterns. Moreover, the network uses langevin differential Dynamics, which avoid overfit, to inverse solve the output node values according to some policy. Nevertheless, having obtained an inverse solution provides the user a modification criterion. Having the modification criterion suggests that information is now according to discretion as a different service or product is a better fit. Lastly, evaluation has been done on several data sets in order to examine the networks performance.