Modeling human thinking about similarities by neuromatrices in the perspective of fuzzy logic

Grobelny, Jerzy
Michalski, Rafal
Weber, Gerhard Wilhelm
In this work, we propose a new method for modeling human reasoning about objects' similarities. We assume that similarity depends on perceived intensities of objects' attributes expressed by natural language expressions such as low, medium, and high. We show how to find the underlying structure of the matrix with intensities of objects' similarities in the factor-analysis-like manner. The demonstrated approach is based on fuzzy logic and set theory principles, and it uses only maximum and minimum operators. Similarly to classic eigenvector decomposition, we aim at representing the initial linguistic ordinal-scale (LOS) matrix as a max-min product of other LOS matrix and its transpose. We call this reconstructing matrix a neuromatrix because we assume that such a process takes place at the neural level in our brain. We show and discuss on simple, illustrative examples, how the presented way of modeling grasps natural way of reasoning about similarities. The unique characteristics of our approach are treating smaller attribute intensities as less important in making decisions about similarities. This feature is consistent with how the human brain is functioning at a biological level. A neuron fires and passes information further only if input signals are strong enough. The proposal of the heuristic algorithm for finding the decomposition in practice is also introduced and applied to exemplary data from classic psychological studies on perceived similarities between colors and between nations. Finally, we perform a series of simulation experiments showing the effectiveness of the proposed heuristic.


Improving reinforcement learning by using sequence trees
Girgin, Sertan; Polat, Faruk; Alhajj, Reda (Springer Science and Business Media LLC, 2010-12-01)
This paper proposes a novel approach to discover options in the form of stochastic conditionally terminating sequences; it shows how such sequences can be integrated into the reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure during the learning process. The constructed tree facilitates the process of identifying frequently used action sequences together with states that are visit...
Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation
Çelikkanat, Hande; Orhan, Guner; Pugeault, Nicolas; Guerin, Frank; Şahin, Erol; Kalkan, Sinan (Institute of Electrical and Electronics Engineers (IEEE), 2016-03-01)
In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make ...
Two approaches for collective learning with language games
Gülçehre, Çağlar; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2011)
This thesis presents a defense of the view that externalism cannot be a theoretical basis of a mentalistic causal-explanatory science, even though such a theoretical basis is implicitly or explicitly adopted by many cognitive scientists. Externalism is a theory in philosophy of mind which states that mental properties are relations between the core realizers of an individual’s mental states (such as brain states) and certain things that exist outside those realizers (such as what the content of a mental sta...
LinGraph: a graph-based automated planner for concurrent task planning based on linear logic
Kortik, Sitar; Saranlı, Uluç (Springer Science and Business Media LLC, 2017-10-01)
In this paper, we introduce an automated planner for deterministic, concurrent domains, formulated as a graph-based theorem prover for a propositional fragment of intuitionistic linear logic, relying on the previously established connection between intuitionistic linear logic and planning problems. The new graph-based theorem prover we introduce improves planning performance by reducing proof permutations that are irrelevant to planning problems particularly in the presence of large numbers of objects and a...
Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network
Kurtuluş, Dilek Funda (Springer Science and Business Media LLC, 2009-05-01)
The ability of artificial neural networks (ANN) to model the unsteady aerodynamic force coefficients of flapping motion kinematics has been studied. A neural networks model was developed based on multi-layer perception (MLP) networks and the Levenberg-Marquardt optimization algorithm. The flapping kinematics data were divided into two groups for the training and the prediction test of the ANN model. The training phase led to a very satisfactory calibration of the ANN model. The attempt to predict aerodynami...
Citation Formats
J. Grobelny, R. Michalski, and G. W. Weber, “Modeling human thinking about similarities by neuromatrices in the perspective of fuzzy logic,” NEURAL COMPUTING & APPLICATIONS, pp. 0–0, 2020, Accessed: 00, 2020. [Online]. Available: