DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications
This addresses the problem of combining symbolic reasoning with subsymbolic learning in sequential applications for AI researchers, representing a novel method rather than an incremental improvement.
The paper tackled the challenge of integrating logical knowledge into deep neural networks for sequential or temporally extended domains with subsymbolic observations by proposing DeepDFA, a neurosymbolic framework that injects temporal logic as differentiable layers, achieving state-of-the-art results in tasks like image sequence classification and policy learning.
Integrating logical knowledge into deep neural network training is still a hard challenge, especially for sequential or temporally extended domains involving subsymbolic observations. To address this problem, we propose DeepDFA, a neurosymbolic framework that integrates high-level temporal logic - expressed as Deterministic Finite Automata (DFA) or Moore Machines - into neural architectures. DeepDFA models temporal rules as continuous, differentiable layers, enabling symbolic knowledge injection into subsymbolic domains. We demonstrate how DeepDFA can be used in two key settings: (i) static image sequence classification, and (ii) policy learning in interactive non-Markovian environments. Across extensive experiments, DeepDFA outperforms traditional deep learning models (e.g., LSTMs, GRUs, Transformers) and novel neuro-symbolic systems, achieving state-of-the-art results in temporal knowledge integration. These results highlight the potential of DeepDFA to bridge subsymbolic learning and symbolic reasoning in sequential tasks.