By Topic

Made-Up Minds:A Constructivist Approach to Artificial Intelligence

Cover Image Copyright Year: 2003
Author(s): Gary L. Drescher
Publisher: MIT Press
Content Type : Books & eBooks
Topics: Computing & Processing
  • Print

Abstract

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.

  •   Click to expandTable of Contents

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Front Matter

      Page(s): i - xv
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Half Title, Title, Copyright, Dedication, Contents, Series foreword, Acknowledgments, Preface View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Constructivist AI

      Page(s): 1
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Introduction and overview

      Page(s): 3 - 22
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 1.1 The schema mechanism: an overview, 1.2 Origins of constructivist AI: on the meaning of learning, 1.3 Guide to the rest of the book View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Synopsis of Piagetian development

      Page(s): 23 - 47
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 2.1 Piagetian fundamentals, 2.2 First stage: reflex activity, solipsist images7, 2.3 Second stage: the coordination of primary schemas, 2.4 Third stage: secondary circular reactions, subjective permanence, 2.5 Fourth stage: coordination of secondary schemas, 2.6 Fifth stage: experiments on objects, 2.7 Sixth stage: simulation of events, 2.8 Subsequent periods: preoperational, concrete and formal operations, 2.9 Themes of Piagetian development View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      The schema mechanism

      Page(s): 49
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Representational elements: structure and use

      Page(s): 51 - 68
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 3.1 Schemas, 3.2 Items, 3.3 Actions, 3.4 Control View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Construction and revision

      Page(s): 51 - 95
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 4.1 MarginaI attribution: spinning off new schemas, 4.2 Synthetic items, 4.3 Composite actions View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Architecture

      Page(s): 97 - 109
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 5.1 Neural architecture, 5.2 Computer implementation architecture View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Performance and speculations

      Page(s): 111
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Synopsis of schema mechanism performance

      Page(s): 113 - 148
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 6.1 The microworid, 6.2 Learning spatial substrates, 6.3 Steps toward intermodal coordination, 6.4 Beginnings of the persistent-object concept, 6.5 Hypothetical scenario of further developments View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Extrapolations: virtual structures, mechanisms

      Page(s): 149 - 165
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 7.1 Virtual generalizations, 7.2 Virtual mechanisms View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Nonnaive Induction

      Page(s): 167 - 175
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 8.1 The problem with naive induction, 8.2 The problem with proposing only nonabsurd generalizations, 8.3 The problem with using only projectable concepts, 8.4 The problem with preferring entrenched concepts, 8.5 Induction conflicts and deductive overrides, 8.6 Why nonnaive induction must be built in, 8.7 Innateness of projectability judgements, 8.8 Induction and counterfactuals View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Appraisal

      Page(s): 177
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Comparisons

      Page(s): 179 - 199
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 9.1 Modularity for learning: prediction-value vs. situation- action systems, 9.2 The schema mechanism and connectionism, 9.3 The schema mechanism and search algorithms, 9.4 The schema mechanism and explanation-based learning, 9.5 The schema mechanism and rational learning, 9.6 Virtual mechanisms and self-modification, 9.7 The schema mechanism and situated activity, 9.8 The schema mechanism and the society of mind, 9.9 Other Piagetian or sensorimotor learning systems View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Conclusions

      Page(s): 201 - 213
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: 10.1 Methodological underpinnings of constructivist AI, 10.2 Directions for future work, 10.3 Evaluation and summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Bibliography

      Page(s): 215 - 218
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Index

      Page(s): 219 - 220
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Back Matter

      Page(s): 221 - 223
      Copyright Year: 2003

      MIT Press eBook Chapters

      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. View full abstract»