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 neurosymbolic 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. The autoritative version of this extended abstract is available at https://arxiv.org/abs/2009.03420v1.
A hybrid neuro-symbolic approach for complex event processing (extended abstract)
Cerutti F.
2020-01-01
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 neurosymbolic 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. The autoritative version of this extended abstract is available at https://arxiv.org/abs/2009.03420v1.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.