[1Q4-J-2] Machine learning: knowledge representation and logic

[1Q4-J-2-02] Learning Logic Programs from Noisy State Transition Data

〇Yin Jun Phua¹, Katsumi Inoue^1,2 (1. Tokyo Institute of Technology, 2. National Institute of Informatics)

Keywords:logic program, neural symbolic

Real world data are often noisy and fuzzy. Most traditional logical machine learning methods require the data to be rst discretized or pre-processed before being able to produce useful output. Such short-coming often limits their application to real world data. On the other hand, neural networks are generally known to be robust against noisy data. However, a fully trained neural network does not provide easily understandable rules that can be used to understand the underlying model. In this thesis, we propose a Differentiable Learning from Interpretation Transition (δ-LFIT) algorithm, that can simultaneously output logic programs fully explaining the state transitions, and also learn from data containing noise and error.