Drescher G. L. (1986) Genetic AI: Translating Piaget into Lisp. Instructional Science 14(3): 357–380. https://cepa.info/2296
Drescher G. L.
(
1986)
Genetic AI: Translating Piaget into Lisp.
Instructional Science 14(3): 357–380.
Fulltext at https://cepa.info/2296
This article presents a constructivist model of human cognitive development during infancy. According to constructivism, the elements of mental representation-even such basic elements as the concept of physical object-are constructed afresh by each individual, rather than being innately supplied. A (partially-specified, yet-unimplemented) mechanism, the Schema Mechanism, is proposed here; this mechanism is intended to achieve a series of cognitive constructions characteristic of infants' sensorimotor-stage development, primarily as described by Piaget. In reference to Piaget's “genetic epistemology”, I call this approach genetic AI-“genetic” not in the sense of genes, but in the sense of genesis: development from the point of origin. The Schema Mechanism focuses on Piaget's concept of the activity and evolution of cognitive schemas. The schema is construed here as a context-sensitive prediction of what will follow a certain action. Schemas are used both as assertions about the world, and as elements of plans to achieve goals. A mechanism of attribution causes a schema's assertion to be extended or revised according to the observed effects of the schema's action; due to the possible relevance of conjunctions of context conditions, the attribution facility needs to be able to sort through a combinatorial explosion of hypotheses. Crucially, the mechanism constructs representations of new actions and state elements, in terms of which schemas are expressed. Included here is a sketch of the proposed Schema Mechanism, and highlights of a hypothetical scenario of the mechanism's operation. The Schema Mechanism starts with a set of sensory and motor primitives as its sole units of representation. As with the Piagetian neonate, this leads to a “solipsist” conception: the world consists of sensory impressions transformed by motor actions. My scenario suggests how the mechanism might progress from there to conceiving of objects in space-representing an object independently of how it is currently perceived, or even whether it is currently perceived. The details of this progression paralledl the Piagetian development of object conception from the first through fifth sensorimotor stage.
Foerster H. von (1972) Perception of the Future and the Future of Perception. Instructional Science 1(1): 31–43. https://cepa.info/1647
Foerster H. von
(
1972)
Perception of the Future and the Future of Perception.
Instructional Science 1(1): 31–43.
Fulltext at https://cepa.info/1647
First paragraph: Truisms have the disadvantage that by dulling the senses they obscure the truth. Almost nobody will become alarmed when told that in times of continuity the future equals the past. Only a few will become aware that from this follows that in times of socio-cultural change the future will not be like the past. Moreover, with a future not clearly perceived, we do not know how to act with only one certainty left: if we don’t act ourselves, we shall be acted upon. Thus, if we wish to be subjects, rather than objects, what we see now, that is, our perception, must be foresight rather than hindsight.
Lawson A. E. & Staver J. R. (1989) Toward a solution of the learning paradox: Emergent properties and neurological principles of constructivism. Instructional Science 18(3): 169–177.
Lawson A. E. & Staver J. R.
(
1989)
Toward a solution of the learning paradox: Emergent properties and neurological principles of constructivism.
Instructional Science 18(3): 169–177.