Mid-level vision

Nakayama, K. (1999). Mid-level vision. In R. A. Wilson & F. C. Keil (Eds.), The MIT encylopedia of the cognitive sciences Cambridge: MIT Press

Nakayama, K. , He, Z.J. and Shimojo, S. Visual surface representation: a critical link between lower-level and higher level vision. In Kosslyn, S.M. and Osherson, D.N. Vision. In Invitation to Cognitive Science. M.I.T. Press, p. 1-70, 1995


http://www.visionlab.harvard.edu/Members/Ken/nakayamapub.htm

Deep Blue versus Garry Kasparov

http://en.wikipedia.org/wiki/Deep_Blue_versus_Garry_Kasparov

Object-based visual search

http://visionlab.harvard.edu/Members/Yaoda/Publications_files/2002_Xu_Perception.pdf

Two componets in percetual learning

Karni, A., & Sagi, D. (1993). The time course of learning a visual skill. Nature, 365,250-252.
http://www.weizmann.ac.il/home/masagi/KarniSagi_Nature93.pdf

High-level perceptual learning

Results show that familiarity speeds visual search and that it does so principally when the distractors, not the targets are familiar.

Wang, Q., Cavanagh, P., & Green, M. (1994). Familiarity and pop-out in visual search. Perception & Psychophysics, 56, 495-500.

Signal enhancement and external noise exclusion

Changes in internal noise have not been found.

:

Dosher, B.A.,& Lu, Z.L. (1999). Mechanisms of perceptual learning. Vision Research 1999, 39, 3197-3221.

Gold, J.M., Bennett, P.J. & Sekuler, A.B. (1999). Signal but not noise changes with perceptual learning. Nature, 402, 176-178.

Gold, J.M., Bennett, P.J. & Sekuler, A.B. (1999). Identification of band-pass filtered letters and faces by human and ideal observers. Vision Research, 39(21), 3537-3560.

Dynamic binding

Hummel, J. E., & Biederman, I. (1992). Dynamic binding in a neural network for shape recognition. Psychological Review, 99, 480-517.
http://www.psych.uiuc.edu/~jehummel/publications.php
cf.
p.510
Timing considerations.

see also,
Biederman, I. (1987). Recognition-by-Components: A Theory of Human Image Understanding. Psychological Review, 94, 115-147.
http://geon.usc.edu/publications.html

p.137, Figure 19.

A symbolic-connectionist theory

A connectionist system based on distributed representations of concept meanings, using temporal synchrony to bind fillers and roles into relational structures.

Hummel, J. E., & Holyoak, K. J. (2003). A symbolic-connectionist theory of relational inference and generalization. Psychological Review, 110, 220-264.
http://www.psych.uiuc.edu/~jehummel/publications.php

The authors present a specific instantiation of their theory in the form of a computer simulation model, Learning and Inference with Schemas and Analogies (LISA).

Hummel's Python LISA
An implementation of Hummel & Holyoak's (2003) LISA, written in Python by John Hummel, is available here.
http://www.psych.uiuc.edu/~jehummel/models.php