An Empirical Evaluation of Recurrent Neural Network Rule Extraction

Rule extraction from black-box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis. Though already a challenging problem in statistical learning in general, the difficulty is even greater when highly non-linear, recursive models, like recurrent neural networks (RNNs), are fit to data. Here, we study the extraction of rules from second order recurrent neural networks (RNNs) trained to recognize the Tomita grammars. We show that production rules can be stably extracted from trained RNNs and that in certain cases the rules outperform the trained RNNs.

[1]  C. Lee Giles,et al.  Higher Order Recurrent Networks and Grammatical Inference , 1989, NIPS.

[2]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[3]  Raymond L. Watrous,et al.  Induction of Finite-State Automata Using Second-Order Recurrent Networks , 1991, NIPS.

[4]  C. L. Giles,et al.  Second-order recurrent neural networks for grammatical inference , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[5]  C. Lee Giles,et al.  Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[6]  Raymond L. Watrous,et al.  Induction of Finite-State Languages Using Second-Order Recurrent Networks , 1992, Neural Computation.

[7]  Padhraic Smyth,et al.  Learning Finite State Machines With Self-Clustering Recurrent Networks , 1993, Neural Computation.

[8]  John F. Kolen,et al.  Fool's Gold: Extracting Finite State Machines from Recurrent Network Dynamics , 1993, NIPS.

[9]  Alberto Sanfeliu,et al.  Active Grammatical Inference: A New Learning Methodology , 1994 .

[10]  P. Tio,et al.  Learning and Extracting Initial Mealy Automata with a Modular Neural Network Model , 1995, Neural Computation.

[11]  Mike Casey,et al.  The Dynamics of Discrete-Time Computation, with Application to Recurrent Neural Networks and Finite State Machine Extraction , 1996, Neural Computation.

[12]  C. Lee Giles,et al.  Constructing deterministic finite-state automata in recurrent neural networks , 1996, JACM.

[13]  C. Lee Giles,et al.  Extraction of rules from discrete-time recurrent neural networks , 1996, Neural Networks.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Giovanni Soda,et al.  Inductive inference from noisy examples using the hybrid finite state filter , 1998, IEEE Trans. Neural Networks.

[16]  C. Lee Giles,et al.  Symbolic Knowledge Representation in Recurrent Neural Networks: Insights from Theoretical Models of , 2000 .

[17]  Henrik Jacobsson,et al.  Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review , 2005, Neural Computation.

[18]  J. Pollack.  The Induction of Dynamical Recognizers , 1996, Machine Learning.

[19]  P. Frasconi,et al.  Representation of Finite State Automata in Recurrent Radial Basis Function Networks , 1996, Machine Learning.

[20]  Alaa A. Kharbouch,et al.  Three models for the description of language , 1956, IRE Trans. Inf. Theory.

[21]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[22]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[23]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[24]  Arthur Szlam,et al.  Automatic Rule Extraction from Long Short Term Memory Networks , 2016, ICLR.