Cognitive Reasoning: A Personal View

The adjective cognitive especially in conjunction with the word computing seems to be a trendy buzzword in the artificial intelligence community and beyond nowadays. However, the term is often used without explicit definition. Therefore we start with a brief review of the notion and define what we mean by cognitive reasoning. It shall refer to modeling the human ability to draw meaningful conclusions despite incomplete and inconsistent knowledge involving among others the representation of knowledge where all processes from the acquisition and update of knowledge to the derivation of conclusions must be implementable and executable on appropriate hardware. We briefly introduce relevant approaches and methods from cognitive modeling, commonsense reasoning, and subsymbolic approaches. Furthermore, challenges and important research questions are stated, e.g., developing a computational model that can compete with a (human) reasoner on problems that require common sense.

[1]  Allen Newell,et al.  Human Problem Solving. , 1973 .

[2]  T. Nagel What is it like to be a Bat , 1974 .

[3]  David Marr,et al.  VISION A Computational Investigation into the Human Representation and Processing of Visual Information , 2009 .

[4]  Krzysztof R. Apt,et al.  Contributions to the Theory of Logic Programming , 1982, JACM.

[5]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[6]  A. Newell Unified Theories of Cognition , 1990 .

[7]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[8]  L. Rips The Psychology of Proof , 1994 .

[9]  Steffen Hölldobler,et al.  Towards a New Massively Parallel Computational Model for Logic Programming , 1994 .

[10]  L. Rips The Psychology of Proof: Deductive Reasoning in Human Thinking , 1994 .

[11]  Douglas B. Lenat,et al.  CYC: a large-scale investment in knowledge infrastructure , 1995, CACM.

[12]  Peter Baumgartner,et al.  Hyper Tableaux , 1996, JELIA.

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

[14]  B. Baars IN THE THEATRE OF CONSCIOUSNESS Global Workspace Theory, A Rigorous Scientific Theory of Consciousness. , 1997 .

[15]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[16]  Herbert A. Simon,et al.  Cognitive modeling in perspective , 1999, Kognitionswissenschaft.

[17]  P. Todd,et al.  Simple Heuristics That Make Us Smart , 1999 .

[18]  Ruth M. J. Byrne,et al.  Deductive reasoning with factual, possible, and counterfactual conditionals , 1999, Memory & cognition.

[19]  Nikolas Kompridis,et al.  So We Need Something Else for Reason to Mean , 2000 .

[20]  R. Selten,et al.  Bounded rationality: The adaptive toolbox , 2000 .

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

[22]  Jonathan Evans In two minds: dual-process accounts of reasoning , 2003, Trends in Cognitive Sciences.

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

[24]  Steffen Hölldobler,et al.  Approximating the Semantics of Logic Programs by Recurrent Neural Networks , 1999, Applied Intelligence.

[25]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[26]  Keith Stenning,et al.  Semantic Interpretation as Computation in Nonmonotonic Logic: The Real Meaning of the Suppression Task , 2005, Cogn. Sci..

[27]  P. Johnson-Laird How We Reason , 2006 .

[28]  Björn Pelzer,et al.  System Description: E-KRHyper , 2007, CADE.

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

[30]  John R. Anderson How Can the Human Mind Occur in the Physical Universe , 2007 .

[31]  Johan Bos,et al.  Linguistically Motivated Large-Scale NLP with C&C and Boxer , 2007, ACL.

[32]  Keith Stenning,et al.  Human Reasoning and Cognitive Science , 2008 .

[33]  Jonathan Evans Dual-processing accounts of reasoning, judgment, and social cognition. , 2008, Annual review of psychology.

[34]  N. Chater,et al.  Précis of Bayesian Rationality: The Probabilistic Approach to Human Reasoning , 2009, Behavioral and Brain Sciences.

[35]  James L. McClelland The Place of Modeling in Cognitive Science , 2009, Top. Cogn. Sci..

[36]  Dov M. Gabbay,et al.  Neural-Symbolic Cognitive Reasoning , 2008, Cognitive Technologies.

[37]  Tamás Gergely,et al.  Cognitive Research , 2009 .

[38]  Steffen Hölldobler,et al.  Logic Programs under Three-Valued Lukasiewicz Semantics , 2009, ICLP.

[39]  Sebastian Bader,et al.  Neural-symbolic integration , 2009 .

[40]  Jennifer Chu-Carroll,et al.  Building Watson: An Overview of the DeepQA Project , 2010, AI Mag..

[41]  Tamás Gergely,et al.  Cognitive Reasoning - A Formal Approach , 2012, Cognitive Technologies.

[42]  Shlomo Geva,et al.  Quo Vadis? Reliable and Practical Rule Extraction from Neural Networks , 2010, Advances in Machine Learning I.

[43]  Hector J. Levesque,et al.  The Winograd Schema Challenge , 2011, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning.

[44]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[45]  Dharmendra S. Modha,et al.  Cognitive Computing , 2011, Informatik-Spektrum.

[46]  D. Kahneman Thinking, Fast and Slow , 2011 .

[47]  Ekaterina Ovchinnikova,et al.  Integration of World Knowledge for Natural Language Understanding , 2012, Atlantis Thinking Machines.

[48]  P. Johnson-Laird,et al.  Theories of the syllogism: A meta-analysis. , 2012, Psychological bulletin.

[49]  Javier Álvez,et al.  Adimen-SUMO: Reengineering an Ontology for First-Order Reasoning , 2012, Int. J. Semantic Web Inf. Syst..

[50]  Steffen Hölldobler,et al.  A Computational Logic Approach to the Suppression Task , 2012, CogSci.

[51]  Zornitsa Kozareva,et al.  SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning , 2011, *SEMEVAL.

[52]  Claudia Schon,et al.  System Description: E-KRHyper 1.4 - Extensions for Unique Names and Description Logic , 2013, CADE.

[53]  Steffen Hölldobler,et al.  A Computational Logic Approach to the Abstract and the Social Case of the Selection Task , 2013 .

[54]  Chris Eliasmith,et al.  How to Build a Brain: A Neural Architecture for Biological Cognition , 2013 .

[55]  Markus Knauff,et al.  A theory and a computational model of spatial reasoning with preferred mental models. , 2013, Psychological review.

[56]  P. Johnson-Laird,et al.  The evaluation of the consistency of quantified assertions , 2014, Memory & cognition.

[57]  Luís Moniz Pereira,et al.  An Abductive Reasoning Approach to the Belief Bias Effect , 2014, KR.

[58]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[59]  Steffen Hölldobler,et al.  Two-Valued Logic is Not Sufficient to Model Human Reasoning, but Three-Valued Logic is: A Formal Analysis , 2016, Bridging@IJCAI.

[60]  Andrew S. Gordon,et al.  Commonsense Interpretation of Triangle Behavior , 2016, AAAI.

[61]  Loizos Michael,et al.  Cognitive Reasoning and Learning Mechanisms , 2016, AIC.

[62]  Steffen Hölldobler,et al.  The Weak Completion Semantics , 2017, Bridging@CogSci.

[63]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[64]  Geoff Sutcliffe The TPTP Problem Library and Associated Infrastructure , 2017, Journal of Automated Reasoning.

[65]  Ido Dagan,et al.  The Recognizing Textual Entailment Challenges: Datasets and Methodologies , 2017 .

[66]  Nathanael Chambers,et al.  LSDSem 2017 Shared Task: The Story Cloze Test , 2017, LSDSem@EACL.

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

[68]  Steffen Hölldobler,et al.  The Syllogistic Reasoning Task: Reasoning Principles and Heuristic Strategies in Modeling Human Clusters , 2017, DECLARE.

[69]  Steffen Hölldobler,et al.  A Computational Logic Approach to Human Syllogistic Reasoning , 2017, CogSci.

[70]  Peter Pagel,et al.  Cognitive Computing , 2018, Informatik-Spektrum.

[71]  Steffen Hölldobler,et al.  A Core Method for the Weak Completion Semantics with Skeptical Abduction , 2018, J. Artif. Intell. Res..

[72]  Andreas Holzinger,et al.  Explainable AI (ex-AI) , 2018, Informatik-Spektrum.

[73]  Stephen Muggleton,et al.  Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP , 2018, Machine Learning.

[74]  Simon Ostermann,et al.  SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge , 2018, *SEMEVAL.

[75]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[76]  Geoff Sutcliffe The 9th IJCAR Automated Theorem Proving System Competition - CASC-J9 , 2018, AI Commun..

[77]  Erik T. Mueller,et al.  Commonsense Reasoning , 2006, Qualitative Representations.

[78]  Ulrich Furbach,et al.  Names Are Not Just Sound and Smoke: Word Embeddings for Axiom Selection , 2019, CADE.

[79]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.