Learning from Interpretation Transition using Feed-Forward Neural Networks

Understanding the evolution of dynamical systems is an ILP topic with many application domains, e.g., multi-agent systems, robotics and systems biology. In this paper, we present a method relying on an artificial neural network (NN) to learn rules describing the evolution of a dynamical system of Boolean variables. The experimental results show the potential of this approach, which opens the way to many extensions naturally supported by NNs, such as the handling of noisy data, continuous variables or time delayed systems.

[1]  S. M. Kamruzzaman,et al.  An Algorithm to Extract Rules from Artificial Neural Networks for Medical Diagnosis Problems , 2010, ArXiv.

[2]  Gilles Bernot,et al.  A Formal Model for Gene Regulatory Networks with Time Delays , 2010, CSBio.

[3]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[4]  Andreas D. Lattner,et al.  Sequential Pattern Mining for Situation and Behavior Prediction in Simulated Robotic Soccer , 2005, RoboCup.

[5]  Daniel Svozil,et al.  Introduction to multi-layer feed-forward neural networks , 1997 .

[6]  Eric Goles Ch.,et al.  Neutral graph of regulatory Boolean networks using evolutionary computation , 2014, 2014 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology.

[7]  R. Caferra.  Logic for Computer Science and Artificial Intelligence , 2011 .

[8]  Richard Bonneau,et al.  DREAM4: Combining Genetic and Dynamic Information to Identify Biological Networks and Dynamical Models , 2010, PloS one.

[9]  Jens Lehmann,et al.  Extracting reduced logic programs from artificial neural networks , 2010, Applied Intelligence.

[10]  Maxim Teslenko,et al.  A SAT-Based Algorithm for Finding Attractors in Synchronous Boolean Networks , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[11]  Katsumi Inoue,et al.  ILP turns 20 - Biography and future challenges , 2012, Mach. Learn..

[12]  Chiaki Sakama,et al.  Learning from interpretation transition , 2013, Machine Learning.

[13]  Joao Marques-Silva,et al.  Prime Compilation of Non-Clausal Formulae , 2015, IJCAI.

[14]  Krysia Broda,et al.  Symbolic knowledge extraction from trained neural networks: A sound approach , 2001, Artif. Intell..

[15]  Harry Wechsler,et al.  From Statistics to Neural Networks: Theory and Pattern Recognition Applications , 1996 .

[16]  Artur S. d'Avila Garcez,et al.  The Connectionist Inductive Learning and Logic Programming System , 1999, Applied Intelligence.

[17]  Chiaki Sakama,et al.  Learning Delayed Influences of Biological Systems , 2015, Front. Bioeng. Biotechnol..