An Approach to Knowledge Extraction From ANN Through Formal Concept Analysis Computational Tool Proposal: SOPHIANN

Abstract

Due to their capability of dealing with nonlinear problems, Artificial Neural Networks (ANN) are widely used with several purposes. Once trained, they are capable to solve unprecedented situations, keeping tolerable errors in their outputs. However, humans cannot assimilate the knowledge kept by those nets, since such knowledge is implicitly represented by their connections weights. So, in order to facilitate the extraction of rules that describe the knowledge of ANN, Formal Concept Analysis (FCA) and rule extraction algorithms as the Next Closure algorithm have been used. In this work, this method is implemented on Sophiann, a computational tool that combines ANN, FCA and the rule extraction algorithms to compute the minimal implication base (Stem Base). As an example, solar energy systems are the domain application considered here, due to their importance as substitutes of traditional energy systems.

Modeling Associative Memories Using Formal Concept Analysis

“…An interesting investigation by Dyce et al improves the cognitive structure of FCA and is being used for discovering ways for better operation of semantic memory of Artificial Intelligence [18]. SOPHIANN is a computational tool modeled for extracting the knowledge from ANN through FCA [19]. Novel cognitive system was proposed that explains how FCA is used exactly to describe human cognitive process [20].…”

FCANN: An Approach to Knowledge Representation From ANN Through Formal Concept Analysis - Application in the Cold Rolling Process

“…In this section, the steps to extract knowledge from neural nets discussed in [5] and [10] will be presented: 1) Select a process representative data set in order to train the ANN. It is defined as:…”

“…To extract knowledge of the cold rolling process, the tool SOPHIANN [10] was used. It is an open source tool composed by modules responsible for the different steps of the approach FCANN.…”

“…This means that the rules represent minimal conditions for the operation points and they determinate the behavior of the process in that point. In [10] a computational tool, SOPHIANN, developed to support this approach was presented. In this work the tool will be used to obtain the implication rules for the metallurgical process of the cold rolling.…”