Rethinking Eliminative Connectionism

@article{Marcus1998RethinkingEC,
  title={Rethinking Eliminative Connectionism},
  author={Gary F. Marcus},
  journal={Cognitive Psychology},
  year={1998},
  volume={37},
  pages={243-282}
}
  • G. Marcus
  • Published 1 December 1998
  • Psychology, Medicine
  • Cognitive Psychology
Humans routinely generalize universal relationships to unfamiliar instances. If we are told "if glork then frum," and "glork," we can infer "frum"; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols and variables; an alternative account holds that symbol-manipulation can be eliminated from scientific… Expand
Can connectionist models of phonology assembly account for phonology?
  • I. Berent
  • Psychology, Medicine
  • Psychonomic bulletin & review
  • 2001
TLDR
An analysis suggests that, unlike GPCs, phonological generalizations may exceed the training space, and eliminative connectionist models of phonology assembly may be unable to provide a complete account for phonology. Expand
Connectionist semantic systematicity
TLDR
This work presents a connectionist model of sentence comprehension that does not implement a symbol system yet behaves systematically, and argues that this systematicity arises robustly and in a psychologically plausible manner because it depends on structure inherent in the world. Expand
Author ' s personal copy Connectionist semantic systematicity
Fodor and Pylyshyn [Fodor, J. A., & Pylyshyn, Z. W. (1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28, 3–71] argue that connectionist models are not able to displayExpand
Constituent similarity and systematicity: The limits of first-order connectionism
TLDR
This work shows that connectionists must develop alternative models, or justify the assumption of similar (non-local) constituent representations prior to the learning task, and suggests reconciling connectionist and classical frameworks to overcome their individual limitations. Expand
Nature, Nurture And Universal Grammar
In just a few years, children achieve a stable state of linguistic competence, making them effectively adults with respect to: understanding novel sentences, discerning relations of paraphrase andExpand
Can connectionism save constructivism?
TLDR
It is shown that the models described in Rethinking Innateness depend on innately assumed representations and that they do not offer a genuine alternative to nativism, and simulation results show that these models are incapable of deriving genuine abstract representations that are not presupposed. Expand
Does Classicism Explain Universality?
  • S. Phillips
  • Psychology, Computer Science
  • Minds and Machines
  • 2004
TLDR
It is argued that universality is also a problem for Classicism in that the syntax-sensitive rules that are supposed to provide causal explanations of mental processes are either too strict, precluding possible generalizations; or too lax, providing no information as to the appropriate alternative. Expand
Connectionism : with or without rules ? Response to
algebraic rules. In their simulations (as in the Marcus et al. experiment) only half the test sequences have the same structure as the sequences used in training. Nonetheless, the learning processExpand
Connectionism and Novel Combinations of Skills: Implications for Cognitive Architecture
TLDR
It is argued that the basic tenets of connectionism, in conjunction with the fact that humans often employ novel combinations of skill modules in rule following and problem solving, lead to the plausible conclusion that, in certain domains, high level cognition requires some form of classical architecture. Expand
Networks are not ‘hidden rules’
TLDR
The purpose of the simulation was to demonstrate that the sequential regularities implicit in Marcus et al.'s stimuli provided a sufficient basis for differentiating sequences that conformed to the 'algebraic rule' from ones that did not, and that having acquired this information, a network could generalize appropriately to novel stimuli. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 109 REFERENCES
Default Generalisation in Connectionist Networks.
TLDR
It is demonstrated that given more appropriate architectural assumptions, connectionist models are perfectly capable of learning a default category and generalising as required, even in the absence of superior type frequency. Expand
German Inflection: The Exception That Proves the Rule
TLDR
This work finds 21 circumstances for regular past tense formation, including novel, unusual-sounding, and rootless and headless derived words; in every case, people inflect them regularly and are evidence for a memory-independent, symbol-concatenating mental operation. Expand
Connectionism and Compositional Semantics
TLDR
It is argued that current neural network architectures are too weak to solve anything but toy language problems, and a hierarchy of classes of connectionist models, from categorizers and associative memories to pattern transformers are dynamic inferencers. Expand
On learning the past-tenses of English verbs: implicit rules or parallel distributed processing
TLDR
It is shown how rule-like behavior can emerge from the interactions among a network of units encoding the root form to past tense mapping, and how details of the acquisition process not captured by the rule account emerge. Expand
From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony
Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency – as though these inferences were a reflexive response of their cognitive apparatus. Furthermore,Expand
The Proper Treatment of Symbols in a Connectionist Architecture
TLDR
Ezinative connectionism offers a direct challenge to the PSS hypothesis, thereby transforming the latter from an axiom of cognitive science into a controversial theoretical position, which has been vigorously Regardless of whether models based on distributed representations provide genuine alternatives to physical symbol systems, it is apparent that they have attractive properties as possible algorithmic accounts of cognition. Expand
Computation and cognition - toward a foundation for cognitive science
TLDR
In Computation and Cognition, Pylyshyn argues that computation must not be viewed as just a convenient metaphor for mental activity, but as a literal empirical hypothesis, which must face a number of serious challenges. Expand
Systematicity: Psychological evidence with connectionist implications
At root, the systematicity debate over classical versus connectionist explanations for cognitive architecture turns on quantifying the degree to which human cognition is systematic. We introduce intoExpand
Psychological and biological models
What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a newExpand
Finding Structure in Time
TLDR
A proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory and suggests a method for representing lexical categories and the type/token distinction is developed. Expand
...
1
2
3
4
5
...