LGML: Logic Guided Machine Learning (Student Abstract)


  • Joseph Scott University of Waterloo
  • Maysum Panju University of Waterloo
  • Vijay Ganesh University of Waterloo




We introduce Logic Guided Machine Learning (LGML), a novel approach that symbiotically combines machine learning (ML) and logic solvers to learn mathematical functions from data. LGML consists of two phases, namely a learning-phase and a logic-phase with a corrective feedback loop, such that, the learning-phase learns symbolic expressions from input data, and the logic-phase cross verifies the consistency of the learned expression with known auxiliary truths. If inconsistent, the logic-phase feeds back "counterexamples" to the learning-phase. This process is repeated until the learned expression is consistent with auxiliary truth. Using LGML, we were able to learn expressions that correspond to the Pythagorean theorem and the sine function, with several orders of magnitude improvements in data efficiency compared to an approach based on an out-of-the-box multi-layered perceptron (MLP).




How to Cite

Scott, J., Panju, M., & Ganesh, V. (2020). LGML: Logic Guided Machine Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13909-13910. https://doi.org/10.1609/aaai.v34i10.7227



Student Abstract Track