Interpreting Finite Automata for Sequential Data

Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specifying objectives or desired attributes. In this paper, we identify the key properties used to interpret automata and propose a modification of a state-merging approach to learn variants of finite state automata. We apply the approach to problems beyond typical grammar inference tasks. Additionally, we cover several use-cases for prediction, classification, and clustering on sequential data in both supervised and unsupervised scenarios to show how the identified key properties are applicable in a wide range of contexts.

[1]  Pedro García,et al.  IDENTIFYING REGULAR LANGUAGES IN POLYNOMIAL TIME , 1993 .

[2]  Ariadna Quattoni,et al.  Spectral learning of weighted automata , 2014, Machine Learning.

[3]  David Lee,et al.  Principles and methods of testing finite state machines-a survey , 1996, Proc. IEEE.

[4]  Colin de la Higuera,et al.  Grammatical Inference: Learning Automata and Grammars , 2010 .

[5]  Cees Witteveen,et al.  Efficiently learning simple timed automata , 2008 .

[6]  Jana Schmidt,et al.  Online Induction of Probabilistic Real-Time Automata , 2012, 2012 IEEE 12th International Conference on Data Mining.

[7]  Walter Daelemans.  Colin de la Higuera: Grammatical inference: learning automata and grammars , 2011, Machine Translation.

[8]  Neil Walkinshaw,et al.  Reverse Engineering State Machines by Interactive Grammar Inference , 2007, 14th Working Conference on Reverse Engineering (WCRE 2007).

[9]  Ryan Turner,et al.  A model explanation system , 2016, 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).

[10]  Qin Lin,et al.  Learning Deterministic Finite Automata from Infinite Alphabets , 2016, ICGI.

[11]  Sicco Verwer,et al.  Short-term Time Series Forecasting with Regression Automata , 2016 .

[12]  Sicco Verwer,et al.  Complementing Model Learning with Mutation-Based Fuzzing , 2016, ArXiv.

[13]  Helmut Veith,et al.  Temporal Logic Model Checking , 2005, Handbook of Networked and Embedded Control Systems.

[14]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[15]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[16]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[17]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[18]  Frits W. Vaandrager,et al.  Applying Automata Learning to Embedded Control Software , 2015, ICFEM.

[19]  Madalina Fiterau,et al.  Trade-offs in Explanatory Model Learning , 2012 .

[20]  Ferdinand Wagner,et al.  Modeling Software with Finite State Machines : A Practical Approach , 2006 .

[21]  Murray Shanahan,et al.  Towards Deep Symbolic Reinforcement Learning , 2016, ArXiv.