• Corpus ID: 34620390

Duality Between Feature and Similarity Models , Based on the Reproducing-Kernel Hilbert Space

@inproceedings{Jones2016DualityBF,
  title={Duality Between Feature and Similarity Models , Based on the Reproducing-Kernel Hilbert Space},
  author={Matt Jones},
  year={2016}
}
There are two longstanding theoretical approaches to learning and concept representation, one based on features and one based on similarity. The feature approach has its roots in associative learning (e.g., Pavlov, 1927) and the idea that learning involves acquiring associations from individual cues to consequential outcomes or responses. Formal models of this learning process assume that any stimulus is decomposable into a set of features, and that learning involves adjusting the associative… 

Figures from this paper

References

SHOWING 1-10 OF 46 REFERENCES

Features of Similarity

TLDR
The metric and dimensional assumptions that underlie the geometric representation of similarity are questioned on both theoretical and empirical grounds and a set of qualitative assumptions are shown to imply the contrast model, which expresses the similarity between objects as a linear combination of the measures of their common and distinctive features.

Toward a unified model of attention in associative learning

TLDR
The discussion summarizes how the approach accounts for a variety of other ‘‘irrational’’ phenomena in associative learning, including base rate effects, perseveration of attention through relevance shifts, overshadowing, and the extrapolation of rules near exceptions.

The Role of Similarity in Generalization

The Role of Similarity in Generalization Matt Jones, W. Todd Maddox, and Bradley C. Love [mattj,maddox,love]@psy.utexas.edu University of Texas, Department of Psychology, 1 University Station A8000

Attention, similarity, and the identification-categorization relationship.

  • R. Nosofsky
  • Psychology
    Journal of experimental psychology. General
  • 1986
TLDR
A unified quantitative approach to modeling subjects' identification and categorization of multidimensional perceptual stimuli is proposed and tested and some support was gained for the hypothesis that subjects distribute attention among component dimensions so as to optimize categorization performance.

Generalization, similarity, and Bayesian inference.

TLDR
Here Shepard's theory is recast in a more general Bayesian framework and it is shown how this naturally extends his approach to the more realistic situation of generalizing from multiple consequential stimuli with arbitrary representational structure.

From conditioning to category learning: an adaptive network model.

TLDR
The adaptive network theory was used to extend the Rescorla-Wagner (1972) least mean squares (LMS) model of associative learning to phenomena of human learning and judgment and the results again support the ResCorla-wagner LMS learning rule as embedded within an adaptive network model.

Attention and learning processes in the identification and categorization of integral stimuli.

  • R. Nosofsky
  • Psychology
    Journal of experimental psychology. Learning, memory, and cognition
  • 1987
TLDR
Evidence was provided that similarity among exemplars decreased as a function of identification learning, and various alternative classification models, including prototype, multiple-prototype, average distance, and "value-on-dimensions" models, were unable to account for the results.

Context theory of classification learning.

TLDR
A context theory of classificatio n is described in which judgments are assumed to derive exclusively from stored exemplar information, and the main idea is that a probe item acts as a retrieval cue to access information associated with stimuli similar to the probe.

On elemental and configural models of associative learning

A Theory of Attention: Variations in the Associability of Stimuli with Reinforcement

TLDR
Overshadowing and blocking are better explained by the choice of an appropriate rule for changing a, such that a decreases to stimuli that signal no change from the probability of reinforcement predicted by other stimuli.