Neural network modeling of altered facial expression recognition in autism spectrum disorders based on predictive processing framework

Abstract

BackgroundThe mechanism underlying the emergence of emotional categories from visual facial expression information during the developmental process is largely unknown. Therefore, this study proposes a system-level explanation for understanding the facial emotion recognition process and its alteration in autism spectrum disorder (ASD) from the perspective of predictive processing theory.MethodsPredictive processing for facial emotion recognition was implemented as a hierarchical recurrent neural network (RNN). The RNNs were trained to predict the dynamic changes of facial expression movies for six basic emotions without explicit emotion labels as a developmental learning process, and were evaluated by the performance of recognizing unseen facial expressions for the test phase. In addition, the causal relationship between the network characteristics assumed in ASD and ASD-like cognition was investigated.ResultsAfter the developmental learning process, emotional categories emerged in the natural course of self-organization in higher-level neurons, even though emotional labels were not explicitly instructed. In addition, the network successfully recognized unseen test facial sequences by adjusting higher-level activity through the process of minimizing precision-weighted prediction error. In contrast, the network simulating altered intrinsic neural excitability demonstrated reduced generalization capability and impaired emotional categorization in higher-level neurons. Consistent with previous findings from human behavioral studies, an excessive precision estimation of noisy details underlies this ASD-like cognition.ConclusionsThese results support the idea that impaired facial emotion recognition in ASD can be explained by altered predictive processing, and provide possible insight for investigating the neurophysiological basis of affective contact.

Application of Higher Education Management in Colleges and Universities by Deep Learning

“…Besides, because most feature extractions have the problem of dimensionality disaster, feature dimensionality reduction is also required. In the end, the expression features are sent to a suitable classifier to complete the expression classification [20,21].…”

Elucidating multifinal and equifinal pathways to developmental disorders by constructing real-world neurorobotic models

“…Another simulation study using the same RNN framework showed that alterations in facial expression recognition can also be explained by unusual precision estimation induced by homogeneous intrinsic neuronal excitability. 73,74 It indicates the possibility of capturing an aspect of the difficulties individuals with ASD have in social interactions. Furthermore, a recent study, combining human performance assessment, functional magnetic resonance imaging, and computational modeling, suggests that spatial neural suppression was weakened in the visual cortex of people with ASD, but no differences were found in the concentrations of excitatory and inhibitory neurotransmitters between typically developing and ASD individuals.…”

Smart Environments for Diverse Cognitive Styles: the Case of Autism

“…This section defends that Autism Spectrum Condition (ASC) can be described and understood as embodied misattunement with a neurotypical (sociocultural) environment (Bolis et al, 2018;Bolis, Dumas and Schilbach, 2023). ASC has been investigated under predictive coding mechanisms (e.g., Pellicano and Burr, 2012;Palmer, Seth and Hohwy, 2015;Fabry, 2018;Perrykkad and Hohwy, 2020;Takahashi et al, 2021). The predictive coding theory generally proposes that the brain generates predictions about the incoming sensory information and updates these predictions based on the actual sensory input, minimising any prediction errors.…”