Made-up minds : a constructivist approach to artificial intelligence
著者
書誌事項
Made-up minds : a constructivist approach to artificial intelligence
（The MIT Press series in artificial intelligence）
MIT Press, c1991
大学図書館所蔵 件 / 全41件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
この図書・雑誌をさがす
注記
Outgrowth of the author's thesis (Ph. D.--Massachusetts Institute of Technology)
Includes bibliographical references (p. [215]-218) and index
内容説明・目次
内容説明
Made-Up Minds addresses fundamental questions of learning and concept invention by means of an innovative computer program that is based on the cognitive-developmental theory of psychologist Jean Piaget. Drescher uses Piaget's theory as a source of inspiration for the design of an artificial cognitive system called the schema mechanism, and then uses the system to elaborate and test Piaget's theory. The approach is original enough that readers need not have extensive knowledge of artificial intelligence, and a chapter summarizing Piaget assists readers who lack a background in developmental psychology. The schema mechanism learns from its experiences, expressing discoveries in its existing representational vocabulary, and extending that vocabulary with new concepts. A novel empirical learning technique, marginal attribution, can find results of an action that are obscure because each occurs rarely in general, although reliably under certain conditions. Drescher shows that several early milestones in the Piagetian infant's invention of the concept of persistent object can be replicated by the schema mechanism.
目次
- Part 1 Constructivist AI: introduction and overview - the schema mechanism - an overview, origins of constructivist AI - on the meaning of learning, guide to the rest of the book
- synopsis of Piagetian development - Piagetian fundamentals, first stage - reflex activity, solipsist images, second stage - the co-ordination of primary schemas, third stage - secondary circular reactions, subjective permanence, fourth stage - co-ordination of secondary schemas, fifth stage - experiments on objects, sixth stage - simulation of events, subsequent periods - preoperational, concrete and formal operations, themes of Piagetian development. Part 2 the schema mechanism: representational elements - structure and use - schemas, items, actions, control
- construction and revision - marginal attribution - spinning off new schemas, synthetic items, composite actions
- architecture - neural architecture, computer implementation architecture. Part 3 Performance and speculations: synopsis of schema mechamism performance - the microworld, learning spatial substrates, steps toward intermodal co-ordination, beginnings of the persistent-object concepts, hypothetical scenario of futher developments
- extrapolations - virtual structures, mechanisms - virtual generalizations, virtual mechanisms
- non-naive induction - the problem with naive induction, the problem with proposing only non-absurd generalizations, the problem with using only projectable concepts, the problem with preferring entrenched concepts, induction conflicts and deductive overrides, why non-niaive induction must be built in, innateness of projectability judgements, induction and counterfactuals. Part 4 Appraisal: comparisons - modularity for learning - prediction-value vs situation-action systems, the schema and mechanism and connectionism, the schema mechanism and search algorithms, the schema mechanism and explanation-based learning, the schema mechanism and rational learning, virtual mechanism and self-modification, the schema mechanism and situated activity, the schema mechanism and the society of mind, other Piagetian or sensorimotor learning systems
- conclusion - methodological underpinnings of constructivist AI, directions for future work, evaluation and summary.
「Nielsen BookData」 より
