Abstract:
This paper presents a theory of how robots may learn concepts by interacting with their environment in an unsupervised way. First, categories of activities are learned, then abstractions over those categories result in concepts. The meanings of concepts are discussed. Robotic systems that learn categories of activities and concepts are presented.
Citations
|
244
|
Women, fire, and dangerous things
– Lakoff
- 1987
|
|
205
|
Family resemblances: Studies in the internal structure of categories
– Rosch, Mervis
- 1975
|
|
122
|
The origins of intelligence
– Piaget
- 1952
|
|
111
|
The Body in the Mind
– Johnson
- 1987
|
|
80
|
On the thresholds of knowledge
– Lenat, Feigenbaum
- 1991
|
|
68
|
How to build a baby: II. Conceptual primitives
– Mandler
- 1992
|
|
49
|
Made-Up Minds
– Drescher
- 1991
|
|
40
|
Eds). Time warps, string edits, and macromolecules: The theory and practice of sequence comparion
– Sankoff, Kruskal
- 1983
|
|
21
|
Continuous Categories for a Mobile Robot
– Cohen
- 1999
|
|
19
|
How to Build a Baby: On the Development of an Accessible Representational System
– Mandler
- 1988
|
|
12
|
The epigenesis of mind: Essays on biology and cognition
– Carey, Erlbaum
- 1994
|
|
8
|
Learning what is relevant to the effects of actions for a mobile robot
– Schmill, Rosenstein, et al.
- 1998
|
|
6
|
do infants learn about the physical world
– How
- 1994
|
|
5
|
Identifying Qualitatively Different Experiences: Experiments with a Mobile Robot
– Oates, M, et al.
- 1999
|