Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experiments
This work addresses how event segmentation is implemented in the brain, contributing to cognitive science and neuroscience, though it appears incremental as it builds on existing event segmentation theory and predictive processing frameworks.
The researchers tackled the problem of how humans segment continuous experience into discrete events by developing a self-supervised neural network model that predicts sensory signals and uses prediction errors to identify event boundaries. They demonstrated that their model's segmentation decisions correlated with human responses (using point-biserial correlation) and formed similar representation spaces to participants when tested on point-light display videos of human behaviors.
People segment complex, ever-changing and continuous experience into basic, stable and discrete spatio-temporal experience units, called events. Event segmentation literature investigates the mechanisms that allow people to extract events. Event segmentation theory points out that people predict ongoing activities and observe prediction error signals to find event boundaries that keep events apart. In this study, we investigated the mechanism giving rise to this ability by a computational model and accompanying psychological experiments. Inspired from event segmentation theory and predictive processing, we introduced a self-supervised model of event segmentation. This model consists of neural networks that predict the sensory signal in the next time-step to represent different events, and a cognitive model that regulates these networks on the basis of their prediction errors. In order to verify the ability of our model in segmenting events, learning them during passive observation, and representing them in its internal representational space, we prepared a video that depicts human behaviors represented by point-light displays. We compared event segmentation behaviors of participants and our model with this video in two hierarchical event segmentation levels. By using point-biserial correlation technique, we demonstrated that event segmentation decisions of our model correlated with the responses of participants. Moreover, by approximating representation space of participants by a similarity-based technique, we showed that our model formed a similar representation space with those of participants. The result suggests that our model that tracks the prediction error signals can produce human-like event boundaries and event representations. Finally, we discussed our contribution to the literature of event cognition and our understanding of how event segmentation is implemented in the brain.