Made-up minds - a constructivist approach to artificial intelligence
Made-up minds - a constructivist approach to artificial intelligence
复制标题
DOI：
10.5860/choice.29-3935
复制
发表时间：
1991
期刊：
影响因子：
--
通讯作者：
G. Drescher
中科院分区：
文献类型：
--
作者：
G. Drescher
第1部分建构主义人工智能：导论和概述-图式机制-概述，建构主义人工智能的起源-关于学习的意义，本书其余部分的指南-皮亚杰发展概要-皮亚杰基础，第一阶段-反射活动，唯我主义者形象，第二阶段-初级图式的协调，第三阶段-次要循环反应，主观永久性，第四阶段-次要图式的协调，第五阶段-关于物体的实验，第六阶段-模拟事件，后续阶段-操作前，具体和正式的操作，皮亚杰发展的主题。第二部分图式机制：表征元素--结构和使用--图式、项、动作、控制构造和修改--边缘归因--衍生新图式、合成项、复合动作结构--神经结构、计算机实现结构。第三部分表现与思考：图式机制表现的概要-微观世界，学习空间基础，走向多式协调的步骤，持久对象概念的开始，进一步发展的假设情景推断-虚拟结构，机制-虚拟概括，虚拟机制非朴素归纳-朴素归纳的问题，只提出非荒谬概括的问题，只使用可投射概念的问题，偏爱根深蒂固的概念的问题，归纳冲突和演绎覆盖，为什么必须建立非nneaive归纳，可投射判断的固有，以及反事实。第四部分评价：比较--学习的模块化--预测--价值与情境-行动系统，图式与机制与联结主义，图式机制与搜索算法，图式机制与基于解释的学习，图式机制与理性学习，虚拟机制与自我修正，图式机制与情境活动，图式机制与心理社会，其他皮亚杰式或感觉运动学习系统，建构主义人工智能的方法论基础，未来工作方向，评价与总结。
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.