@article{Scott_Panju_Ganesh_2020, title={LGML: Logic Guided Machine Learning (Student Abstract)}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/7227}, DOI={10.1609/aaai.v34i10.7227}, abstractNote={<p>We introduce <em>Logic Guided Machine Learning</em> (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 <em>learning-phase</em> and a <em>logic-phase</em> 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).</p>}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Scott, Joseph and Panju, Maysum and Ganesh, Vijay}, year={2020}, month={Apr.}, pages={13909-13910} }