Logic Negation with Spiking Neural P Systems

Nowadays, the success of neural networks as reasoning systems is doubtless. Nonetheless, one of the drawbacks of such reasoning systems is that they work as black-boxes and the acquired knowledge is not human readable. In this paper, we present a new step in order to close the gap between connectionist and logic based reasoning systems. We show that two of the most used inference rules for obtaining negative information in rule based reasoning systems, the so-called Closed World Assumption and Negation as Finite Failure can be characterized by means of spiking neural P systems, a formal model of the third generation of neural networks born in the framework of membrane computing.

[1]  Danny De Schreye,et al.  Answer Set Planning , 1999 .

[2]  Saratha Sathasivam,et al.  Kernel machine to doing logic programming in Hopfield network for solve non horn problem-3sat , 2017 .

[3]  Gadi Pinkas,et al.  Symmetric Neural Networks and Propositional Logic Satisfiability , 1991, Neural Computation.

[4]  Gheorghe Paun,et al.  The Oxford Handbook of Membrane Computing , 2010 .

[5]  Linqiang Pan,et al.  Cell-like spiking neural P systems , 2016, Theor. Comput. Sci..

[6]  Henry N. Adorna,et al.  Spiking neural P systems with structural plasticity , 2015, Neural Computing and Applications.

[7]  Son N. Tran,et al.  Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Takashi Ikegami,et al.  Reactive, Proactive, and Inductive Agents: An Evolutionary Path for Biological and Artificial Spiking Networks , 2019, Frontiers in Computational Neuroscience.

[9]  Zhengyou He,et al.  Fault Diagnosis of Electric Power Systems Based on Fuzzy Reasoning Spiking Neural P Systems , 2015, IEEE Transactions on Power Systems.

[10]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Xiangxiang Zeng,et al.  Spiking Neural P Systems with Thresholds , 2014, Neural Computation.

[12]  Anthony Kulis,et al.  Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies , 2009, Scalable Comput. Pract. Exp..

[13]  Pascal Hitzler,et al.  Mathematical Aspects of Logic Programming Semantics , 2010, Chapman and Hall / CRC studies in informatics series.

[14]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[15]  Linqiang Pan,et al.  Spiking neural P systems with request rules , 2016, Neurocomputing.

[16]  Lalana Kagal,et al.  J un 2 01 8 Explaining Explanations : An Approach to Evaluating Interpretability of Machine Learning , 2018 .

[17]  Robert A. Kowalski,et al.  The Semantics of Predicate Logic as a Programming Language , 1976, JACM.

[18]  Feng Yang.  Duality in Logic Programming , 1991 .

[19]  Richard J. Duro,et al.  Open-Ended Learning: A Conceptual Framework Based on Representational Redescription , 2018, Front. Neurorobot..

[20]  Pascal Hitzler,et al.  Perspectives of Neural-Symbolic Integration , 2007, Studies in Computational Intelligence.

[21]  Tao Wang,et al.  Fault Classification of Power Transmission Lines Using Fuzzy Reasoning Spiking Neural P Systems , 2016, BIC-TA.

[22]  Raymond Reiter.  On Closed World Data Bases , 1977, Logic and Data Bases.

[23]  Alexander Binder,et al.  Explaining nonlinear classification decisions with deep Taylor decomposition , 2015, Pattern Recognit..

[24]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[25]  Linqiang Pan,et al.  Spiking Neural P Systems With Communication on Request and Mute Rules , 2017, IEEE Transactions on Parallel and Distributed Systems.

[26]  Oscar H. Ibarra,et al.  On spiking neural P systems , 2006, Natural Computing.

[27]  Daniel Díaz-Pernil,et al.  Semantics of deductive databases with spiking neural P systems , 2018, Neurocomputing.

[28]  Krzysztof R. Apt,et al.  Logic Programming and Negation: A Survey , 1994, The Journal of Logic Programming.

[29]  Alois Knoll,et al.  A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks , 2018, Front. Neurorobot..

[30]  Kai-Uwe Kühnberger,et al.  Towards integrated neural–symbolic systems for human-level AI: Two research programs helping to bridge the gaps , 2015, BICA 2015.

[31]  Kai-Uwe Kühnberger,et al.  Neural-Symbolic Learning and Reasoning: A Survey and Interpretation , 2017, Neuro-Symbolic Artificial Intelligence.

[32]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[33]  Miguel A. Gutiérrez-Naranjo,et al.  Deductive databases and P systems , 2004, Comput. Sci. J. Moldova.

[34]  Antonis C. Kakas,et al.  Default Reasoning via Negation as Failure , 1992, ECAI Workshop on Knowledge Representation and Reasoning.

[35]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[36]  Artiom Alhazov,et al.  Forward and Backward Chaining with P Systems , 2011, Int. J. Nat. Comput. Res..

[37]  J. Lloyd.  Foundations of Logic Programming , 1984, Symbolic Computation.

[38]  Xiangrong Liu,et al.  Asynchronous spiking neural P systems with rules on synapses , 2015, Neurocomputing.

[39]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[40]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[41]  Keith L. Clark,et al.  Negation as Failure , 1987, Logic and Data Bases.

[42]  Joxan Jaffar,et al.  Completeness of the Negation as Failure Rule , 1983, IJCAI.

[43]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .