2 papers
cs.LG2025
Understanding Boolean Function Learnability on Deep Neural Networks: PAC Learning Meets Neurosymbolic Models
Marcio Nicolau, Anderson R. Tavares, Zhiwei Zhang +4
Computational learning theory states that many classes of boolean formulas are learnable in polynomial time. This paper addresses the understudied subject of how, in practice, such…
cs.LG2025
Towards a Neural Lambda Calculus: Neurosymbolic AI Applied to the Foundations of Functional Programming
João Flach, Alvaro F. Moreira, Luis C. Lamb
Over the last decades, deep neural networks based-models became the dominant paradigm in machine learning. Further, the use of artificial neural networks in symbolic learning has b…