NeuPSL: Neural Probabilistic Soft Logic. (arXiv:2205.14268v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2205.14268

We present Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic
(NeSy) framework that unites state-of-the-art symbolic reasoning with the
low-level perception of deep neural networks. To explicitly model the boundary
between neural and symbolic representations, we introduce NeSy Energy-Based
Models, a general family of energy-based models that combine neural and
symbolic reasoning. Using this framework, we show how to seamlessly integrate
neural and symbolic parameter learning and inference. We perform an extensive
empirical evaluation and show that NeuPSL outperforms existing …

arxiv lg logic neural