Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Inference of Abstraction for a Unified Account of Reasoning and Learning (2402.09046v1)

Published 14 Feb 2024 in cs.AI, cs.LG, and cs.LO

Abstract: Inspired by Bayesian approaches to brain function in neuroscience, we give a simple theory of probabilistic inference for a unified account of reasoning and learning. We simply model how data cause symbolic knowledge in terms of its satisfiability in formal logic. The underlying idea is that reasoning is a process of deriving symbolic knowledge from data via abstraction, i.e., selective ignorance. The logical consequence relation is discussed for its proof-based theoretical correctness. The MNIST dataset is discussed for its experiment-based empirical correctness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. Neural module networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 39–48, 2016.
  2. A Bayesian Extension of the Description Logic π’œβ’β„’β’π’žπ’œβ„’π’ž\cal{ALC}caligraphic_A caligraphic_L caligraphic_C, volume 11468, pages 339–354. Springer, Cham, JELIA 2019 lncs edition, 2019.
  3. Bayes in the brain: On Bayesian modelling in neuroscience. The British Journal for the Philosophy of Science, 63:697–723, 2012.
  4. A theory of learning to infer. Psychol Rev., 127(3):412–441, 2020.
  5. Learning probabilistic relational models. In Proc. 16th Int. Joint Conf. on Artif. Intell., pages 1297–1304, 1996.
  6. Karl Friston. The history of the future of the Bayesian brain. Neuroimage, 62-248(2):1230–1233, 2012.
  7. Neural substrate of dynamic Bayesian inference in the cerebral cortex. Nature Neuroscience, 19:1682–1689, 2016.
  8. A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In Proc. Int. Joint Conf. on Neural Networks, pages 1812–1817, 2005.
  9. Jakob Hohwy. The Predictive Mind. Oxford University Press, University of Oxford, 2014.
  10. Nils J.Nilsson. Probabilistic logic. Artificial Intelligence, 28:71–87, 1986.
  11. The Bayesian brain: the role of uncertainty in neural coding and computation. Trends in Neurosciences, 27:712–719, 2004.
  12. Human-level concept learning through probabilistic program induction. Science, 350(6266):1332–1338, 2015.
  13. Building machines that learn and think like people. Behavioral and Brain Sciences, 40(e253):1–72, 2017.
  14. Hierarchical Bayesian inference in the visual cortex. Journal of Optical Society of America, 20:1434–1448, 2003.
  15. Judea Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann; 1st edition, Burlington, Massachusetts, 1988.
  16. Judea Pearl. Probabilistic Semantics for Nonmonotonic Reasoning, pages 157–188. Cambridge, MA: The MIT Press, philosophy and AI: essays at the interface edition, 1991.
  17. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
  18. Rajesh P.Β N. Rao and DanaΒ H. Ballard. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neuroscience, 2:79–87, 1999.
  19. Markov logic networks. Machine Learning, 62:107–136, 2006.
  20. Artificial Intelligence : A Modern Approach, Third Edition. Pearson Education, Inc., London, England, 2009.
  21. Bayesian brains without probabilities. Trends in Cognitive Sciences, 20:883–893, 2016.
  22. Probabilistic inferences from conjoined to iterated conditionals. Int. Journal of Approximate Reasoning, 93:103–118, 2018.
  23. Taisuke Sato. A statistical learning method for logic programs with distribution semantics. In Proc. 12th int. conf. on logic programming, pages 715–729, 1995.
  24. Theory-based Bayesian models of inductive learning and reasoning. Trends in Cognitive Sciences, 10(7):309–318, 2006.
  25. Matthias Thimm. Inconsistency measures for probabilistic logics. Artif. Intell., 197:1–24, 2013.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (1)
  1. Hiroyuki Kido (10 papers)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets