Self-organized inductive reasoning with NeMuS
This work addresses inductive learning in logic-based AI, but appears incremental as it builds on existing ILP-like methods without clear broad impact.
The paper introduced Neural Multi-Space (NeMuS), a weighted multi-space representation for first-order logic, and demonstrated its use in reasoning and inductive learning, with initial experiments analyzing its suitability for generating concept regions based on attributes.
Neural Multi-Space (NeMuS) is a weighted multi-space representation for a portion of first-order logic designed for use with machine learning and neural network methods. It was demonstrated that it can be used to perform reasoning based on regions forming patterns of refutation and also in the process of inductive learning in ILP-like style. Initial experiments were carried out to investigate whether a self-organizing the approach is suitable to generate similar concept regions according to the attributes that form such concepts. We present the results and make an analysis of the suitability of the method in the process of inductive learning with NeMuS.