Logic Tensor Networks

Attempts at combining logic and neural networks into neurosymbolic approaches have been on the increase in recent years. In a system, symbolic knowledge assists deep learning, which typically uses sub-symbolic distributed representation, to learn reason higher level of abstraction. We present Logic Tensor Networks (LTN), framework that supports querying, learning reasoning with both rich data abstract about world. LTN introduces fully differentiable logical language, called Real Logic, whereby elements first-order signature are grounded onto using computational graphs fuzzy semantics. show provides uniform language represent compute efficiently many most important AI tasks such as multi-label classification, relational clustering, semi-supervised regression, embedding query answering. implement illustrate each above several simple explanatory examples TensorFlow 2. The results indicate can be general powerful for AI.