The Symbol Grounding Problem

ABSTRACT: There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the "symbol grounding problem": How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: (1) "iconic representations" , which are analogs of the proximal sensory projections of distal objects and events, and (2) "categorical representations" , which are learned and innate feature-detectors that pick out the

This circumscribed complementary role for connectionism in a hybrid system seems to remedy the weaknesses of the two current competitors in their attempts to model the mind independently. In a pure symbolic model the crucial connection between the symbols and their referents is missing; an autonomous symbol system, though amenable to a systematic semantic interpretation, is ungrounded. In a pure connectionist model, names are connected to objects through invariant patterns in their sensory projections, learned through exposure and feedback, but the crucial compositional property is missing;…

saved by

• Lydia Nottingham

related reading

• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• [2304.01481] The Vector Grounding Problemarxiv.org
• ChatGPT4 on the cat on the mat – Skywritingsgeneric.wordpress.soton.ac.uk
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• The Building Blocks of Interpretabilitydistill.pub
• The Platonic Representation Hypothesisphillipi.github.io
• Learning and Reasoning in Symbolic Domains | The Center for Brains, Minds & Machinescbmm.mit.edu
• Neuro-symbolic AI - Wikipediaen.wikipedia.org
• On the Learnability of Physical Concepts: Can a Neural Network Understand What’s Real?arxiv.org
• pdfopenreview.net
• The binding problemmaxhodak.com
• Dynamics of Symmetry Group Theorizinglaetusinpraesens.org