NeSyA: Neurosymbolic Automata
This work addresses the problem of developing neurosympholic AI for temporal domains, which is incremental as it builds on existing symbolic automata and neural methods.
The paper tackled the lack of neurosympholic AI systems for sequential/temporal problems by integrating symbolic automata with neural perception for sequence classification and tagging, resulting in a model that scales or performs more accurately than previous systems in a synthetic benchmark and improves generalization in a real-world event recognition task.
Neurosymbolic (NeSy) AI has emerged as a promising direction to integrate neural and symbolic reasoning. Unfortunately, little effort has been given to developing NeSy systems tailored to sequential/temporal problems. We identify symbolic automata (which combine the power of automata for temporal reasoning with that of propositional logic for static reasoning) as a suitable formalism for expressing knowledge in temporal domains. Focusing on the task of sequence classification and tagging we show that symbolic automata can be integrated with neural-based perception, under probabilistic semantics towards an end-to-end differentiable model. Our proposed hybrid model, termed NeSyA (Neuro Symbolic Automata) is shown to either scale or perform more accurately than previous NeSy systems in a synthetic benchmark and to provide benefits in terms of generalization compared to purely neural systems in a real-world event recognition task.