A Hybrid Neuro-Symbolic Approach for Complex Event Processing

TL;DR

This paper introduces a hybrid neuro-symbolic system for complex event processing that combines neural networks with logical rules, enabling effective learning from limited data and accurate event classification.

Contribution

It presents a novel neuro-symbolic architecture based on Event Calculus that improves learning efficiency and classification accuracy in complex event detection tasks.

Findings

Requires less labeled data than pure neural networks

Capable of end-to-end event classification

Outperforms pure neural network approaches on urban sound dataset

Abstract

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.