9780195370676

Principles of Synthetic Intelligence PSI: An Architecture of Motivated Cognition

by
  • ISBN13:

    9780195370676

  • ISBN10:

    0195370678

  • Format: Hardcover
  • Copyright: 2009-04-06
  • Publisher: Oxford University Press

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

Purchase Benefits

  • Free Shipping On Orders Over $35!
    Your order must be $35 or more to qualify for free economy shipping. Bulk sales, PO's, Marketplace items, eBooks and apparel do not qualify for this offer.
  • Get Rewarded for Ordering Your Textbooks! Enroll Now
List Price: $83.00 Save up to $8.30
  • Rent Book $74.70
    Add to Cart Free Shipping

    TERM
    PRICE
    DUE

Supplemental Materials

What is included with this book?

  • The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.
  • The Rental copy of this book is not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

Summary

From the Foreword: "In this book Joscha Bach introduces Dietrich Dorner's PSI architecture and Joscha's implementation of the MicroPSI architecture. These architectures and their implementation have several lessons for other architectures and models. Most notably, the PSI architecture includes drives and thus directly addresses questions of emotional behavior. An architecture including drives helps clarify how emotions could arise. It also changes the way that the architecture works on a fundamental level, providing an architecture more suited for behaving autonomously in a simulated world. PSI includes three types of drives, physiological (e.g., hunger), social (i.e., affiliation needs), and cognitive (i.e., reduction of uncertainty and expression of competency). These drives routinely influence goal formation and knowledge selection and application. The resulting architecture generates new kinds of behaviors, including context dependent memories, socially motivated behavior, and internally motivated task switching. This architecture illustrates how emotions and physical drives can be included in an embodied cognitive architecture. The PSI architecture, while including perceptual, motor, learning, and cognitive processing components, also includes several novel knowledge representations: temporal structures, spatial memories, and several new information processing mechanisms and behaviors, including progress through types of knowledge sources when problem solving (the Rasmussen ladder), and knowledge-based hierarchical active vision. These mechanisms and representations suggest ways for making other architectures more realistic, more accurate, and easier to use. The architecture is demonstrated in the Island simulated environment. While it may look like a simple game, it was carefully designed to allow multiple tasks to be pursued and provides ways to satisfy the multiple drives. It would be useful in its own right for developing other architectures interested in multi-tasking, long-term learning, social interaction, embodied architectures, and related aspects of behavior that arise in a complex but tractable real-time environment. The resulting models are not presented as validated cognitive models, but as theoretical explorations in the space of architectures for generating behavior. The sweep of the architecture can thus be larger-it presents a new cognitive architecture attempting to provide a unified theory of cognition. It attempts to cover perhaps the largest number of phenomena to date. This is not a typical cognitive modeling work, but one that I believe that we can learn much from." --Frank E. Ritter, Series Editor Although computational models of cognition have become very popular, these models are relatively limited in their coverage of cognition-- they usually only emphasize problem solving and reasoning, or treat perception and motivation as isolated modules. The first architecture to cover cognition more broadly is PSI theory, developed by Dietrich Dorner. By integrating motivation and emotion with perception and reasoning, and including grounded neuro-symbolic representations, PSI contributes significantly to an integrated understanding of the mind. It provides a conceptual framework that highlights the relationships between perception and memory, language and mental representation, reasoning and motivation, emotion and cognition, autonomy and social behavior. It is, however, unfortunate that PSI's origin in psychology, its methodology, and its lack of documentation have limited its impact. The proposed book adapts Psi theory to cognitive science and artificial intelligence, by elucidating both its theoretical and technical frameworks, and clarifying its contribution to how we have come to understand cognition.

Table of Contents

Machines to explain the mindp. 3
From psychology to computational modelingp. 6
Classes of cognitive modelsp. 16
Symbolic systems and the Language of Thought Hypothesisp. 19
Cognition without representation?p. 24
Machines of cognitionp. 26
Cognitive science and the computational theory of mindp. 26
Classical (symbolic) architectures: Soar and ACT-Rp. 31
Hybrid architecturesp. 37
Alternatives to symbolic systems: Distributed architecturesp. 38
Agent architecturesp. 42
Cognition and Affect-A conceptual analysis of cognitive systemsp. 45
Dorner's "blueprint for a mind"p. 53
Terminological remarksp. 55
An overview of the PSI theory and PSI agentsp. 57
A simple autonomous vehiclep. 64
An outline of the PSI agent architecturep. 68
Representation of and for mental processesp. 75
Neural representationsp. 75
Associators and dissociatorsp. 77
Cortex fields, activators, inhibitors and registersp. 78
Sensor neurons and motor neuronsp. 78
Sensors specific to cortex fieldsp. 79
Quadsp. 79
Partonomiesp. 81
Alternatives and subjunctionsp. 83
Sensory schemasp. 84
Effector/action schemasp. 85
Tripletsp. 86
Space and timep. 87
Basic relationshipsp. 89
Memory organizationp. 92
Episodic schemasp. 93
Behavior programsp. 93
Protocol memoryp. 95
Abstraction and analogical reasoningp. 98
Taxonomiesp. 101
Perceptionp. 102
Expectation horizonp. 103
Orientation behaviorp. 104
HyPerceptp. 104
How HyPercept worksp. 105
Modification of HyPercept according to the Resolution Levelp. 108
Generalization and specializationp. 109
Treating occlusionsp. 110
Assimilation of new objects into schemasp. 110
Situation imagep. 111
Mental stagep. 113
Managing knowledgep. 113
Reflectionp. 114
Categorization ("What is it and what does it do?")p. 115
Symbol groundingp. 116
Behavior control and action selectionp. 119
Appetence and aversionp. 120
Motivationp. 121
Urgesp. 122
Motivesp. 122
Demandsp. 123
Fuel and waterp. 123
Intactness ("Integritäet;t", integrity, pain avoidance)p. 124
Certainty ("Bestimmtheit", uncertainty reduction)p. 124
Competence ("Kompetenz", efficiency, control)p. 126
Affiliation ("Okayness", legitimacy)p. 128
Motive selectionp. 129
Intentionsp. 132
Actionp. 133
Automatismsp. 134
Simple Planningp. 134
"What can be done?"-the Trial-and-error strategyp. 136
Modulatorsp. 137
Activation/Arousalp. 138
Selection threshold.p. 139
Resolution levelp. 139
Sampling rate/securing behaviorp. 140
The dynamics of modulationp. 141
Emotionp. 143
Classifying the PSI theory's emotion modelp. 145
Emotion as a continuous multidimensional spacep. 147
Emotion and motivationp. 151
Emotional phenomena that are modeled by the PSI theoryp. 152
Language and future avenuesp. 157
Language comprehensionp. 158
Matching language symbols and schemsp. 159
Parsing grammatical languagep. 159
Handling ambiguityp. 162
Learning languagep. 163
Communicationp. 164
Problem solving with languagep. 166
"General Problem Solver"p. 167
Araskamp. 167
Antagonistic dialoguep. 168
Language and consciousnessp. 169
Directions for future developmentp. 171
Döet;rner's PSI agent implementationp. 173
The Island simulationp. 173
PSI agentsp. 178
Perceptionp. 180
Motive generation (Genlnt)p. 181
Intention selection (Selectlnt)p. 182
Intention executionp. 183
Events and situations in EmoRegul and Island agentsp. 183
Modulatorsp. 185
Pleasure and displeasurep. 186
The behavior cycle of the PSI agentp. 188
Emotional expressionp. 192
From PSI to MicroPSI: Representations in the PSI modelp. 195
Properties of the existing PSI modelp. 197
A formal look at PSI's worldp. 199
Modeling the environmentp. 202
Analyzing basic relationsp. 204
The missing "is-a" relationp. 207
Unlimited storage-limited retrievalp. 209
The mechanics of representationp. 210
Solving the Symbol Grounding Problemp. 211
Localism and distributednessp. 219
Missing links: technical deficitsp. 222
Missing powers: Conceptual shortcomingsp. 226
The passage of timep. 226
The difference between causality and successionp. 226
Individuals and identityp. 227
Semantic rolesp. 229
The MicroPSI architecturep. 233
A framework for cognitive agentsp. 234
Towards MicroPSI agentsp. 237
Architectural overviewp. 238
Componentsp. 240
Representations in MicroPSI: Executable compositional hierarchiesp. 246
Definition of basic elementsp. 247
Representation using compositional hierarchiesp. 254
Executionp. 258
Execution of hierarchical scriptsp. 260
Script execution with chunk nodesp. 263
The MicroPSI Frameworkp. 265
Componentsp. 266
The node net editor and simulatorp. 268
Creation of agentsp. 270
Creation of entitiesp. 271
Manipulation of entitiesp. 272
Running an agentp. 273
Monitoring an agentp. 273
Providing an environment for agent simulationp. 274
The world simulatorp. 276
Setting up a worldp. 278
Objects in the worldp. 279
Connecting agentsp. 280
Special display optionsp. 280
Controlling agents with node nets: an examplep. 282
Implementing a PSI agent in the MicroPSI frameworkp. 286
The world of the SimpleAgentp. 288
The main control structures of the SimpleAgentp. 289
The motivational systemp. 292
Perceptionp. 295
Simple hypothesis based perception (HyPercept)p. 296
Integration of low-level visual perceptionp. 297
Navigationp. 300
Summary: The PSI theory as a model of cognitionp. 303
Main assumptionsp. 304
Parsimony in the PSI theoryp. 312
What makes Döet;rner's agents emotional?p. 314
Is the PSI theory a theory of human cognition?p. 318
Tackling the "Hard Problem"p. 321
Referencesp. 325
Author Indexp. 358
Subject Indexp. 363
Table of Contents provided by Ingram. All Rights Reserved.

Rewards Program

Write a Review