Open AccessDesigning arithmetic neural primitive for sub-symbolic aggregation of linguistic assessments
Author(s) -
Demidovskij Alexander,
Eduard Babkin
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1680/1/012007
Subject(s) - computer science , representation (politics) , the symbolic , block (permutation group theory) , arithmetic , artificial neural network , fuzzy logic , product (mathematics) , artificial intelligence , theoretical computer science , mathematics , psychology , geometry , politics , political science , psychoanalysis , law
The very first step towards a challenging goal of creation of monolithic generic neuro-symbolic systems is application of sub-symbolic ideas to particular symbolic algorithms like aggregation of fuzzy linguistic assessments during Linguistic Decision Making. A novel theoretical idea is to express this aggregation as structural manipulations and translate them in a neuroalgorithm. Tensor Product Representation (TPR) methodology provides a generic framework of designing neural networks that do not require training and produce an exact result equivalent to the result of symbolic algorithms. This paper demonstrates design of TPR-based arithmetic as a basic building block for expressing linguistic assessments aggregation on a sub-symbolic level and a neural architecture for the basic arithmetic operation.