Formalising and Learning a Quantum Model of Concepts

In this report we present a new modelling framework for concepts based on quantum theory, and demonstrate how the conceptual representations can be learned automatically from data. A contribution of the work is a thorough category-theoretic formalisation of our framework. We claim that the use of category theory, and in particular the use of string diagrams to describe quantum processes, helps elucidate some of the most important features of our quantum approach to concept modelling. Our approach builds upon Gardenfors' classical framework of conceptual spaces, in which cognition is modelled geometrically through the use of convex spaces, which in turn factorise in terms of simpler spaces called domains. We show how concepts from the domains of shape, colour, size and position can be learned from images of simple shapes, where individual images are represented as quantum states and concepts as quantum effects. Concepts are learned by a hybrid classical-quantum network trained to perform concept classification, where the classical image processing is carried out by a convolutional neural network and the quantum representations are produced by a parameterised quantum circuit. We also use discarding to produce mixed effects, which can then be used to learn concepts which only apply to a subset of the domains, and show how entanglement (together with discarding) can be used to capture interesting correlations across domains. Finally, we consider the question of whether our quantum models of concepts can be considered conceptual spaces in the Gardenfors sense.

[1]  Taco Cohen,et al.  Weakly supervised causal representation learning , 2022, NeurIPS.

[2]  S. Clark,et al.  The Conceptual VAE , 2022, ArXiv.

[3]  S. Tull A Categorical Semantics of Fuzzy Concepts in Conceptual Spaces , 2021, ACT.

[4]  B. Coecke,et al.  Composing Conversational Negation , 2021, ACT.

[5]  B. Stöger An Invitation to Applied Category Theory. Seven Sketches in Compositionality. By Brendan Fong and David I. Spivak. Cambridge University Press, 2019. Paperback, pp. 348. Price GBP 37.99. ISBN 9781108711821. , 2021, Acta crystallographica. Section A, Foundations and advances.

[6]  Dan Shiebler,et al.  Category Theory in Machine Learning , 2021, ArXiv.

[7]  Benjamin Rodatz,et al.  Conversational Negation using Worldly Context in Compositional Distributional Semantics , 2021, SEMSPACE.

[8]  Richard Tanburn,et al.  Formalising Concepts as Grounded Abstractions , 2021, ArXiv.

[9]  J. V. D. Wetering,et al.  Constructing quantum circuits with global gates , 2020, New Journal of Physics.

[10]  Iordanis Kerenidis,et al.  Nearest centroid classification on a trapped ion quantum computer , 2020, npj Quantum Information.

[11]  Fei Yan,et al.  QHSL: A quantum hue, saturation, and lightness color model , 2020, Inf. Sci..

[12]  Martha Lewis,et al.  Towards logical negation for compositional distributional semantics , 2020, FLAP.

[13]  Marcello Benedetti,et al.  Parameterized quantum circuits as machine learning models , 2019, Quantum Science and Technology.

[14]  Bernhard Schölkopf,et al.  Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , 2018, ICML.

[15]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[16]  M. Schuld,et al.  Circuit-centric quantum classifiers , 2018, Physical Review A.

[17]  Maria Schuld,et al.  Quantum Machine Learning in Feature Hilbert Spaces. , 2018, Physical review letters.

[18]  Walter Vinci,et al.  Quantum variational autoencoder , 2018, Quantum Science and Technology.

[19]  Bart Jacobs,et al.  Disintegration and Bayesian inversion via string diagrams , 2017, Mathematical Structures in Computer Science.

[20]  Murray Shanahan,et al.  SCAN: Learning Hierarchical Compositional Visual Concepts , 2017, ICLR.

[21]  Kai-Uwe Kühnberger,et al.  A Thorough Formalization of Conceptual Spaces , 2017, KI.

[22]  Aleks Kissinger,et al.  Picturing Quantum Processes: A First Course in Quantum Theory and Diagrammatic Reasoning , 2017 .

[23]  Martha Lewis,et al.  Interacting Conceptual Spaces I : Grammatical Composition of Concepts , 2017, Conceptual Spaces: Elaborations and Applications.

[24]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[25]  Jonathan Lawry,et al.  Hierarchical conceptual spaces for concept combination , 2016, Artif. Intell..

[26]  Bernhard Ganter,et al.  Conceptual Exploration , 2016, Springer Berlin Heidelberg.

[27]  Julian N. Marewski,et al.  What can the brain teach us about building artificial intelligence? , 2016, Behavioral and Brain Sciences.

[28]  Tomas Veloz,et al.  Unitary Transformations in the Quantum Model for Conceptual Conjunctions and Its Application to Data Representation , 2015, Front. Psychol..

[29]  David Schlangen,et al.  Simple Learning and Compositional Application of Perceptually Grounded Word Meanings for Incremental Reference Resolution , 2015, ACL.

[30]  P. Gärdenfors The Geometry of Meaning: Semantics Based on Conceptual Spaces , 2014 .

[31]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[32]  J. Busemeyer,et al.  Can quantum probability provide a new direction for cognitive modeling? , 2013, The Behavioral and brain sciences.

[33]  John Preskill,et al.  Quantum computing and the entanglement frontier , 2012, 1203.5813.

[34]  Jennifer Trueblood,et al.  A Quantum Probability Account of Order Effects in Inference , 2011, Cogn. Sci..

[35]  P. Selinger A Survey of Graphical Languages for Monoidal Categories , 2009, 0908.3347.

[36]  Diederik Aerts,et al.  Quantum Structure in Cognition , 2008, 0805.3850.

[37]  John T. Rickard,et al.  Reformulation of the theory of conceptual spaces , 2007, Inf. Sci..

[38]  Martin B. Plenio,et al.  An introduction to entanglement measures , 2005, Quantum Inf. Comput..

[39]  Gregory L. Murphy The Big Book of Concepts , 2002 .

[40]  Janet Aisbett,et al.  A general formulation of conceptual spaces as a meso level representation , 2001, Artif. Intell..

[41]  Concepts , 2020, Encyclopedia of Education and Information Technologies.

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

[43]  S. Laurence,et al.  The Conceptual Mind: New Directions in the Study of Concepts , 2015 .

[44]  D. Gross,et al.  Proceedings, 25th Solvay Conference on Physics: The Theory of the Quantum World , 2013 .

[45]  P. Panangaden Probabilistic Relations , 1998 .

[46]  A. Gopnik,et al.  Words, thoughts, and theories , 1997 .

[47]  H. Dishkant,et al.  Logic of Quantum Mechanics , 1976 .

[48]  N. Foo Conceptual Spaces—The Geometry of Thought , 2022 .