Grammatical Inference using an Adaptive Recurrent Neural Network

摘要

In this study, we proposed an adaptive recurrent neural network that is capable of inferring a regular grammar, and at the same time of extracting the underlying grammatical rules emulated by a finite-state automata. Our proposed network adapts from an initial analog phase, which has good training behavior, to a discrete phase for automatic rule extraction. A modified objective function is proposed to accomplish the discretisation process as well as logic learning. Comparison on learning Tomita grammars shows that our network has a significant advantage over other approaches.