Logic Tensor Network (LTN) is a neurosymbolic framework that supports querying, learning and reasoning with both rich data and rich abstract knowledge about the world. LTN uses a differentiable first-order logic language, called Real Logic, to incorporate data and logic.

LTN converts Real Logic formulas into TensorFlow computational graphs. Such formulas can express complex queries about the data, prior knowledge to satisfy during learning, statements to prove, etc.