A Hybrid Neuro-Symbolic Approach for Complex Event Processing
This addresses the challenge of complex event processing for applications like urban sound monitoring, though it appears incremental as it combines existing neural and symbolic techniques.
The paper tackles the problem of detecting complex event patterns with sparse data by proposing a hybrid neuro-symbolic architecture based on Event Calculus, which requires much fewer labeled examples than pure neural networks and achieves competitive classification performance on an Urban Sounds 8K dataset.
Training a model to detect patterns of interrelated events that form situations of interest can be a complex problem: such situations tend to be uncommon, and only sparse data is available. We propose a hybrid neuro-symbolic architecture based on Event Calculus that can perform Complex Event Processing (CEP). It leverages both a neural network to interpret inputs and logical rules that express the pattern of the complex event. Our approach is capable of training with much fewer labelled data than a pure neural network approach, and to learn to classify individual events even when training in an end-to-end manner. We demonstrate this comparing our approach against a pure neural network approach on a dataset based on Urban Sounds 8K.