ABSTRACT:

Artificial Neural Networks are nonlinear techniques which typically provide one of the most accurate predictive models perceiving faces in terms of the social impressions they make on people. However, they are often not suitable to be used in many practical application domains because of their lack of transparency and comprehensibility. This paper proposes a new neuro-fuzzy method to investigate the characteristics of the facial images perceived as Iyashi by one hundred and fourteen subjects. Iyashi is a Japanese word used to describe a peculiar phenomenon that is mentally soothing, but is yet to be clearly defined. In order to gain a clear insight into the reasoning made by the nonlinear prediction models such as holographic Neural Networks (HNN) in the classification of Iyashi expressions, the interpretability of the proposed fuzzy-quantized HNN (FQHNN) is improved by reducing the number of input parameters, creating membership functions and extracting fuzzy rules from the responses provided by the subjects about a limited dataset of 20 facial images. The experimental results show that the proposed FQHNN achieves 2-8% increase in the prediction accuracy compared with traditional neuro-fuzzy classifiers while it extracts 35 fuzzy rules explaining what characteristics a facial image should have in order to be classified as Iyashi-stimulus for 87 subjects.