Related Topics: chinese room argument, cognitive modelling, computationalism, connectionism, hermeneutics, intentionality, referential competence, other minds problem, robotics, situatedness/embeddedness, Turing test.

Searle's celebrated Chinese Room Argument has shaken the foundations of Artificial Intelligence. Many refutations have been attempted, but none seem convincing. This paper is an attempt to sort out explicitly the assumptions and the logical, methodological and empirical points of disagreement. Searle is shown to have underestimated some features of computer modeling, but the heart of the issue turns out to be an empirical question about the scope and limits of the purely symbolic (computational) model of the mind. Nonsymbolic modeling turns out to be immune to the Chinese Room Argument. The issues discussed include the Total Turing Test, modularity, neural modeling, robotics, causality and the symbol-grounding problem.
 
 

The symbol grounding problem
Physica D  42: 335-346.
 

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 invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations," grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z"). Connectionism is one natural candidate for the mechanism that learns the invariant features underlying categorical representations, thereby connecting names to the proximal projections of the distal objects they stand for. In this way connectionism can be seen as a complementary component in a hybrid nonsymbolic/symbolic model of the mind, rather than a rival to purely symbolic modeling. Such a hybrid model would not have an autonomous symbolic "module," however; the symbolic functions would emerge as an intrinsically "dedicated" symbol system as a consequence of the bottom-up grounding of categories' names in their sensory representations. Symbol manipulation would be governed not just by the arbitrary shapes of the symbol tokens, but by the nonarbitrary shapes of the icons and category invariants in which they are grounded.
 

Other Bodies, Other Minds: A Machine Incarnation of an Old Philosophical Problem
Minds and Machines 1: 43-54.
 

Explaining the mind by building machines with minds runs into the other-minds problem: How can we tell whether any body other than our own has a mind when the only way to know is by being the other body? In practice we all use some form of Turing Test: If it can DO everything a body with a mind can do such that we can't tell them apart, we have no basis for doubting it has a mind. But what is "everything" a body with a mind can do? Turing's original "pen-pal" version (the TT) only tested linguistic capacity, but Searle has shown that a mindless symbol-manipulator could pass the TT undetected. The Total Turing Test (TTT) calls for all of our linguistic and robotic capacities; immune to Searle's argument, it suggests how to ground a symbol manipulating system in the capacity to pick out the objects its symbols refer to. No Turing Test, however, can guarantee that a body has a mind. Worse, nothing in the explanation of its successful performance requires a model to have a mind at all. Minds are hence very different from the unobservables of physics (e.g., superstrings); and Turing Testing, though essential for machine-modeling the mind, can really only yield an explanation of the body. 1992  

Connectionism and computationalism are currently vying for hegemony in cognitive modeling. At first glance the opposition seems incoherent, because connectionism is itself computational, but the form of computationalism that has been the prime candidate for encoding the "language of thought" has been symbolic computationalism, whereas connectionism is nonsymbolic, or, as some have hopefully dubbed it, "subsymbolic"). This paper will examine what is and is not a symbol system. A hybrid nonsymbolic/symbolic system will be sketched in which the meanings of the symbols are grounded bottom-up in the system's capacity to discriminate and identify the objects they refer to. Neural nets are one possible mechanism for learning the invariants in the analog sensory projection on which successful categorization is based. "Categorical perception," in which similarity space is "warped" in the service of categorization, turns out to be exhibited by both people and nets, and may mediate the constraints exerted by the analog world of objects on the formal world of symbols.
 

The predominant approach to cognitive modeling is still what has come to be called "computationalism," the hypothesis that cognition is computation. The more recent rival approach is "connectionism," the hypothesis that cognition is a dynamic pattern of connections and activations in a "neural net." Are computationalism and connectionism really deeply different from one another, and if so, should they compete for cognitive hegemony, or should they collaborate? These questions will be addressed here, in the context of an obstacle that is faced by computationalism (as well as by connectionism if it is either computational or seeks cognitive hegemony on its own): The symbol grounding problem.

The following commentaries are available, each with a response:

Boyle, C. Franklin Transduction and Degree of Grounding

Bringsjord, Selmer People Are Infinitary Symbol Systems: No Sensorimotor Capacity Neccessary

Dietrich, Eric The Ubiquity of Computation

Dyer, Michael G. Computationalism, Neural Networks and Minds, Analog or Otherwise

Fetzer, James H. The TTT is not the Final Word

Hayes, Pat Computers Don't Follow Instructions

Honavar, Vasant A Note on the Symbol Grounding Problem and its Solution

Kentridge, R.W. Computation, Chaos and Non-Deterministic Symbolic Computation: The Chinese Room Problem Solved?

MacLennan, Bruce J. Grounding Analog Computers

McDermott, Drew The Digital Computer as Red Herring

Powers, David M. W. A Grounding of Definition

Roitblat, Herbert L. Computational Grounding

Searle, John R. The Failures of Computationalism

An alternative site: article

"Symbol Grounding" is beginning to mean too many things to too many people. My own construal has always been simple: Cognition cannot be just computation, because computation is just the systematically interpretable manipulation of meaningless symbols, whereas the meanings of my thoughts don't depend on their interpretability or interpretation by someone else. On pain of infinite regress, then, symbol meanings must be grounded in something other than just their interpretability if they are to be candidates for what is going on in our heads. Neural nets may be one way to ground the names of concrete objects and events in the capacity to categorize them (by learning the invariants in their sensorimotor projections). These grounded elementary symbols could then be combined into symbol strings expressing propositions about more abstract categories. Grounding does not equal meaning, however, and does not solve any philosophical problems.

The former paper includes replies to the following papers:

Dorffner, G. & E. Prem  Connectionism, symbol grounding, and autonomous agents

Gassner, M.   The structure grounding problem

Brooks, R.A.   The engineering of physical grounding

Christiansen M.H. & N. Chater   Symbol grounding – The emperor’s new theory of meaning?
 

What is the relationship between cognitive theories of symbol grounding and philosophical theories of meaning? In this paper the authors argue that, although often considered to be fundamentally distinct, the two are actually very similar. Both set out to explain how non-referring atomic tokens or states of a system can acquire status as semantic primitives within that system. In view of this close relationship, the authors consider what attempts to solve these problems can gain from each other. They argue that, at least presently, work on symbol grounding is not likely to have an impact on philosophical theories of meaning. On the other hand, the authors suggest that the symbol grounding theorists have a lot to learn from their philosophical counterparts. In particular, the former must address the problems that have been identified in attempting to formulate philosophical theories of reference.
 
Lakoff, G.   Grounded concepts without symbols

Touretzky, D.S.  The heart of symbols: Why symbol grounding is irrelevant
 
 

Both Artificial Life and Artificial Mind are branches of what Dennett has called "reverse engineering": Ordinary engineering attempts to build systems to meet certain functional specifications, reverse bioengineering attempts to understand how systems that have already been built by the Blind Watchmaker work. Computational modelling (virtual life) can capture the formal principles of life, perhaps predict and explain it completely, but it can no more be alive than a virtual forest fire can be hot. In itself, a computational model is just an ungrounded symbol system; no matter how closely it matches the properties of what is being modelled, it matches them only formally, with the mediation of an interpretation. Synthetic life is not open to this objection, but it is still an open question how close a functional equivalence is needed in order to capture life. Close enough to fool the Blind Watchmaker is probably close enough, but would that require molecular indistinguishability, and if so, do we really need to go that far?
 

Computation is interpretable symbol manipulation. Symbols are objects that are manipulated on the basis of rules operating only on the symbols' shapes , which are arbitrary in relation to what they can be interpreted as meaning. Even if one accepts the Church/Turing Thesis that computation is unique, universal and very near omnipotent, not everything is a computer, because not everything can be given a systematic interpretation; and certainly everything can't be given every systematic interpretation. But even after computers and computation have been successfully distinguished from other kinds of things, mental states will not just be the implementations of the right symbol systems, because of the symbol grounding problem: The interpretation of a symbol system is not intrinsic to the system; it is projected onto it by the interpreter. This is not true of our thoughts. We must accordingly be more than just computers. My guess is that the meanings of our symbols are grounded in the substrate of our robotic capacity to interact with that real world of objects, events and states of affairs that our symbols are systematically interpretable as being about.
 

Cognitive science is a form of "reverse engineering" (as Dennett has dubbed it). We are trying to explain the mind by building (or explaining the functional principles of) systems that have minds. A "Turing" hierarchy of empirical constraints can be applied to this task, from t1, toy models that capture only an arbitrary fragment of our performance capacity, to T2, the standard "pen-pal" Turing Test (total symbolic capacity), to T3, the Total Turing Test (total symbolic plus robotic capacity), to T4 (T3 plus internal [neuromolecular] indistinguishability). All scientific theories are underdetermined by data. What is the right level of empirical constraint for cognitive theory? I will argue that T2 is underconstrained (because of the Symbol Grounding Problem and Searle's Chinese Room Argument) and that T4 is overconstrained (because we don't know what neural data, if any, are relevant). T3 is the level at which we solve the "other minds" problem in everyday life, the one at which evolution operates (the Blind Watchmaker is no mind-reader either) and the one at which symbol systems can be grounded in the robotic capacity to name and manipulate the objects their symbols are about. I will illustrate this with a toy model for an important component of T3 -- categorization -- using neural nets that learn category invariance by "warping" similarity space the way it is warped in human categorical perception: within-category similarities are amplified and between-category similarities are attenuated. This analog "shape" constraint is the grounding inherited by the arbitrarily shaped symbol that names the category and by all the symbol combinations it enters into. No matter how tightly one constrains any such model, however, it will always be more underdetermined than normal scientific and engineering theory. This will remain the ineliminable legacy of the mind/body problem.
 

Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding
(with S.J. Hanson and J. Lubin)
In: J. V. Honavar and  L. Uhr (eds). Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration. New York: Academic Press. Pp. 191-206.

After people learn to sort objects into categories they see them differently. Members of the same category look more alike and members of different categories look more different. This phenomenon of within-category compression and between-category separation in similarity space is called categorical perception (CP). It is exhibited by human subjects, animals and neural net models. In backpropagation nets trained first to auto-associate 12 stimuli varying along a one-dimensional continuum and then to sort them into 3 categories, CP arises as a natural side-effect because of four factors: (1) Maximal interstimulus separation in hidden-unit space during auto-association learning, (2) movement toward linear separability during categorization learning, (3) inverse-distance repulsive force exerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially in interpolating CP to untrained regions of the continuum. Once similarity space has been "warped" in this way, the compressed and separated "chunks" have symbolic labels which could then be combined into symbol strings that constitute propositions about objects. The meanings of such symbolic representations would be "grounded" in the system's capacity to pick out from their sensory projections the object categories that the propositions were about.
 

It is hypothesized that words originated as the names of perceptual categories and that two forms of representation underlying perceptual categorization, iconic and categorical representations, served to ground a third, symbolic, form of representation. The third form of representation made it possible to name and describe our environment, chiefly in terms of categories, their memberships, and their invariant features. Symbolic representations can be shared because they are intertranslatable. Both categorization and translation are approximate rather than exact, but the approximation can be made as close as we wish. This is the central property of that universal mechanism for sharing descriptions that we call natural language.
 

2.  Literature on the symbol grounding problem.

Christiansen, M.H. & Chater, N. (1992). Connectionism, meaning and learning. Connection Science  4: 227-252.

Dorffner, G., Prem, E. & Trost, H. (1993)  Words, Symbols, and Symbol Grounding, Österreichisches Forschungsinstitut für Artificial Intelligence, Wien, TR-93-30.
 [available online at ftp://ftp.ai.univie.ac.at/papers/oefai-tr-93-30.ps.z]

Dyer, M. (1990).  Intentionality and computationalism: minds, machines, Searle and Harnad. Journal of Experimental and Theoretical Artificial Intelligence 2: 303-19.
 

Plunkett, K., Sinha, C., Moller, M.F., Strandsby, O. (1992).  Symbol grounding or the emergence of symbols? Vocabulary growth in children and a connectionist net.  Connection Science, 4(3-4), special issue: Philosophical issues in connectionist modelling, A. Clark (ed.), pp. 293-312.

Prem, E. (1994). Symbol grounding revisited. Österreichisches Forschungsinstitut für Artificial Intelligence, Wien, TR-94-19.
 [available online at ftp://ftp.ai.univie.ac.at/papers/oefai-tr-94-19.ps.z]

Prem, E. (1994). Symbol grounding and transcendental logic. Österreichisches Forschungsinstitut für Artificial Intelligence, Wien, TR-94-20.
 [available online at ftp://ftp.ai.univie.ac.at/papers/oefai-tr-93-30.ps.z]

Prem, E. (1995). Dynamic symbol grounding state construction and the problem of teleology. in Mira J. & Sandoval F. (eds.), From Natural to Artificial Neural Computation, Proc. International Workshop on Artificial Neural Networks, Malaga-Torremolinos, Spain, June. Springer, LNCS 930.

Prem, E. (1995). Symbol grounding and transcendental logic. In Niklasson L. & Boden M. (eds.), Current Trends in Connectionism, Lawrence Erlbaum, Hillsdale, NJ, pp. 271-282.

Sales, N.J. and  Evans, R.G. (1989). An approach to solving the symbol grounding problem: neural networks for object naming and retrieval. Proc. of CMC-95, Eindhoven.