Abstract:
Using neural nets to simulate learning and the genetic algorithm to simulate evolution in a toy world of mushrooms and mushroom-foragers, we place two ways of acquiring categories into direct competition with one another: In (1) "sensorimotor toil," new categories are acquired through real-time, feedbackcorrected, trial and error experience in sorting them. In (2) "symbolic theft," new categories are acquired by hearsay from propositions -- boolean combinations of symbols describing them. In competition, symbolic theft always beats sensorimotor toil. We hypothesize that this is the basis of the adaptive advantage of language. Entry-level categories must still be learned by toil, however, to avoid an infinite regress (the "symbol grounding problem"). Changes in the internal representations of categories must take place during the course of learning by toil. These changes can be analyzed in terms of the compression of within-category similarities and the expansion of between-category dif...
Citations
|
2044
|
Learning internal representations by error propagation
– Rumelhart, G, et al.
- 1986
|
|
895
|
The Ecological Approach to Visual Perception
– Gibson
- 1986
|
|
531
|
The symbol grounding problem
– Harnad
- 1990
|
|
81
|
Categorical perception: the groundwork of cognition
– Harnad
- 1987
|
|
70
|
Syntax without natural selection: how compositionality emerges from vocabulary in a population of learners
– Kirby
- 2000
|
|
68
|
Econets: Neural Networks that Learn in a Environment
– Parisi, Cecconi
- 1990
|
|
65
|
Influences of categorization on perceptual discrimination
– Goldstone
- 1994
|
|
27
|
Categorical perception effects induced by category learning
– Livingston, Andrews
- 1998
|
|
26
|
Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding
– Harnad, Hanson, et al.
- 1994
|
|
19
|
Grounding symbols in the analog world with neural nets
– Harnad
- 1993
|
|
13
|
Warping similarity space in category learning by backprop nets
– Tijsseling, Harnad
- 1997
|
|
12
|
The origin of words: A psychophysical hypothesis
– Harnad
- 1996
|
|
12
|
Grounding symbols through evolutionary language games
– Steels
- 2001
|
|
11
|
Connecting object to symbol in modeling cognition
– Harnad
- 1992
|
|
11
|
Categorical Perception and the Evolution of Supervised Learning in Neural Nets
– Harnad, Hanson, et al.
- 1991
|
|
9
|
Grounding symbolic capacity in robotic capacity
– Harnad
- 1995
|
|
6
|
Evolution of a rapidly learned representation for speech
– Nakisa, Plunkett
- 1998
|
|
4
|
Warping similarity space in category learning by human subjects: The role of task difficulty
– Pevtzow, Harnad
- 1997
|
|
4
|
From hand to mouth: Some critical stages in the evolution of language. In: S. Harnad et al
– Steklis, Harnad
- 1976
|
|
3
|
On the interaction of prior knowledge and stimulus structure in category learning
– Livingston, Andrews
- 1995
|
|
2
|
Experimental analysis of naming behavior cannot explain naming capacity
– Harnad
- 1996
|
|
1
|
Induction, evolution and accountability. Annals of the New York Academy of Sciences 280:58
– Harnad
- 1976
|