Thinking Machine.

Format:

Book

Author/Creator:

Zhu, Ping.

Series:

Computer Science, Technology and Applications Series

Language:

English

Subjects (All):

Artificial intelligence.

Semantic computing.

Physical Description:

1 online resource (350 pages)

Edition:

1st ed.

Place of Publication:

New York : Nova Science Publishers, Incorporated, 2024.

Summary:

This book authored by Professor Ping Zhu explores the theoretical and technical foundations of artificial intelligence with a focus on interpretable intelligence and thinking machines. It examines the ultimate goal of surpassing human cognition through innovative research and technical approaches. Topics include fundamental AI theories such as language entropy, semantic inheritance, and creative thinking simulation, along with system architecture and program engineering. The book provides in-depth discussions on the mathematical principles, adaptive mechanisms, and semantic frameworks required for machine thinking. Intended for researchers, professionals, and academics in artificial intelligence and related fields, the text combines comprehensive theoretical insights with practical applications and examples to advance understanding of AI's potential. Generated by AI.

Contents:

Intro

Contents

Preface

Chapter 1

Introduction

1.1. Sensation Input

1.2. Thinking Component

1.3. Result Output

1.3.1. Problem Space

1.3.2. Knowledge Representation

1.3.3. Adaptive Progressive Improvement of System Architecture

Chapter 2

Fundamental Theories

2.1. Language Entropy Theory

2.1.1. Concept Definitions

2.1.2. Fisheye-Driven Model

2.1.3. Deeply Related Issues

2.1.3.1. Commonsense Judgment

2.1.3.2. Focus Shifting

2.1.3.3. Distance Reasoning

2.1.3.4. Semantic Echoes and Redundancies

2.1.3.5. Reference Resolution

2.1.3.6. Semantic Conflicts

2.1.3.7. Semantic Supplements

2.1.3.8. Semantic Accumulation

2.1.3.9. The Twelve Sensations

2.1.3.10. Paper Abstract

2.2. Semantic Inheritance and Overloading Theory

2.2.1. Technology Route

2.2.1.1. Chat/Dialogue

2.2.1.2. Storytelling

2.2.1.3. Problem Resolving

2.2.2. Semantic Framework and Scene Division

2.2.3. Local Semantic Supplementation and Global Semantic Accumulation

2.2.3.1. Global Semantic Identifier Strings

2.2.3.2. Data Element Variable Naming

2.2.4. Application Fields

2.2.4.1. Chat/Dialogue

2.2.4.2. Storytelling

2.2.4.3. Problem Resolving

2.2.5. Large Language Model-Related Issues

2.3. Big Decision Tree Theory

2.3.1. Necessity

2.3.2. Key Contents

2.3.3. Implementation Technology

2.3.3.1. Adaptive Data Structure

2.3.3.2. Adaptive Adjustment of Program Patterns

2.3.3.3. Automatic Association Adjustment of Software Workflow

2.3.3.4. Dynamic Addition of Basic Logic Conditions

2.3.3.5. System Adaptive Running Mechanism

2.3.3.6. Data-Driven Storage and Operation of the Big Decision Tree System

2.4. Mathematical Principles for Machine Thinking

2.4.1. Main Content

2.4.1.1. Semantic Framework Matching.

2.4.1.2. Mathematical Concept/Object Recognizing

2.4.1.3. Iterative Deducing of Calculation Rules

2.4.1.4. Comprehensive Thinking Mechanism

2.4.2. Progressive Recognizing of Mathematic Concepts/Objects

2.4.2.1. Local Semantic Annotating

2.4.2.2. Semantic Matrix Diagram

2.4.2.3. Function Modules

2.4.2.4. Global Semantic Progressive Aggregation Algorithm

2.4.2.5. Semantic Conflict Discrimination

2.5. Creative Thinking Theory

2.5.1. Formalization Theory for Image Thinking

2.5.2. Creative Thinking Simulation Theory Based on Features Analogy

Chapter 3

System Architecture

3.1. Software Architecture

3.2. Logic Architecture

3.2.1. Adaptive Mechanism Activation

3.2.2. Adaption Implementation

3.2.3. Commonsense Knowledge Base Construction

3.2.4. Running Mechanism Determination

3.2.5. Dynamic Adjustment of Variable Internal Structures

3.2.6. Adaptive Result Output

3.3. Program Structure

3.3.1. Robust Programming

3.3.2. Framework-Oriented Programming

3.4. Semantic Engineering Platform Architecture

3.5. Module Architecture for Humanoid Automatic Resolution of Mathematic Application Problems

3.6. Adaptive Technology Application

Chapter 4

Machine Implementation for Image Thinking

4.1. Semantic Accumulation

4.1.1. Equivalent Association Patterns

4.1.2. Equivalent Condition Associations

4.1.3. Equivalent Inequality Relations

4.1.4. Equivalent Condition Inequality Relations

4.1.5. Equivalent Relations

4.1.6. Commonsense Concepts and Attribute Relationships

4.1.7. Dynamic Semantic Circle

4.1.8. Semantic Frameworks

4.1.9. Semantic Inheritance and Overloading

4.1.10. Semantic Engineering Platform

4.2. Image Thinking Computation Model

4.3. Application Examples

4.3.1. Line Segment Method

4.3.2. Enumeration Method.

4.3.2.1. Semantic Annotation

4.3.2.2. Data Element Variable Table

4.3.2.3. Dynamic Semantic Circle

4.3.2.4. Data Representation Framework for Enumeration

4.3.3. Circle Method

4.3.3.1 Source Problem

4.3.3.2. Logic Expansion

4.3.4. Train Crossing Bridge Method

4.3.4.1. Source Problem

4.3.4.2. Logic Expansion

4.4. Deep Reflection on the Formal Theory for Image Thinking

Chapter 5

Features Analogy Theory for Creative Thinking

5.1. "Knowledge Representation + Commonsense Judgment" for Creative Thinking Theory

5.2. "Use Case Analysis + Meta Patterns" for Creative Thinking Theory

5.2.1. Archimedean Crown Problem

5.2.2. Cao Chong Weight Elephant

5.3. "Rumination Computing + Trend Predicting + Commonsense Judging" for Creative Thinking Theory

5.3.1. Time-Interval Extension

5.3.2. Target-Angle Extension

5.3.3. Discussion on Deep Extension

5.4. Semantic Digitizing and Semantic Distance Computing

5.4.1. Semantic Constraint Theory

5.4.2. Technique Implementation

5.4.2.1. "Anchor Points" Data System

5.4.2.2. Knowledge System

5.4.2.3. Variable Retrieval Pattern

5.4.2.4. Multidimensional Semantic Distance Computing

5.4.2.5. Attribute Constraint Relaxing and Threshold Setting

5.4.2.6. Intent Verification Mechanism

5.4.3. Instances Analysis

5.4.3.1. Circular Runway Problem

5.4.3.2. Circular Track Problem

5.5. Sample Accumulation and Commonsense Knowledge Base

5.5.1. Source Example

5.5.2. Application Example

5.6. Several Issues

Chapter 6

Semantic Engineering

6.1. Domain Problem Analysis

6.2. Semantic Knowledge Accumulation

6.2.1. Semantic Knowledge Types

6.2.2. Dynamic Semantic Generation

6.2.3. System Management

6.3. Example of Gradual Semantic Accumulation

6.3.1. Variable Recognition

6.3.2. Commonsense Relationship Identification.

6.3.3. Dynamic Semantic Circle

6.3.4. Problem Resolving

6.4. Discussion

Chapter 7

Thinking Engineering

7.1. Comprehensive Thinking Model

7.2. Integrated Processing

7.2.1. Identification and Assignment Values for the Formula Variables

7.2.2. Mathematic Formula Derivation

7.2.3. Logic Condition Derivation

7.2.4. Logic Knowledge Base Accessing

7.2.5. Logic Reasoning and Semantic Correspondence Verification

7.2.6. Semantic Conflict Discrimination

7.3. Key Functions Implementation

7.3.1. Preprocessing

7.3.2. Semantic Annotation

7.3.3. Semantic Framework Matching

7.3.4. Scene Semantic Analysis

7.3.5. Data Element Variable Naming

7.3.6. Dynamic Computing and Logic Relationship Generation

7.3.7. Comprehensive Thinking by Use Cases

7.3.8. Integrating Thinking Mechanisms Based on the Blackboard Model

7.4. Logic Extension for Machine Thinking

7.4.1. Machine Thinking Generalization Ability Improvement

7.4.2. Machine Thinking Reasoning Mode Extension

Chapter 8

Program Engineering

8.1. Development Architecture and State Monitoring

8.2. Framework-Oriented Programming Idea

8.2.1. Object-Oriented Programming Technology

8.2.2. Running State Monitoring

8.2.3. Logic Judgment Condition Optimizing

8.2.4. Multidimensional Approximate Computing

8.2.5. Dynamic Document Description System

8.3. Framework-Oriented Integrated Development Environment

8.3.1. Function Unit Framework

8.3.2. Universal Function I/O Interface

8.3.3. Logic Conflict Location Tool

8.3.4. Library Functions and Fundamental Classes

8.3.5. Data, Commonsense, and Domain Knowledge Integration Tools

8.4. Framework-Oriented Programming Examples

8.4.1. Reference Annotations

8.4.2. Key Data Structures

8.4.3. Running Mechanism

8.4.5. Running Mode

8.5. Robust Programming.

8.5.1. Design Theory

8.5.1.1. Design Principles

8.5.1.2. Logic Decision-Making System

8.5.1.3. Semantic Loss Calculation

8.5.1.4. Data Dependency Relationship of the Basic Logic Conditions

8.5.1.5. Robustness of Logic Condition

8.5.1.6. Other Instructions

8.5.2. Core Algorithm

8.5.2.1. Key Data Structures

8.5.2.2. System initialization

8.5.2.3. Core Algorithm

8.5.2.4. Supplementary Explanation

8.5.3. Application Examples

8.5.3.1. Semantic Annotation

8.5.3.2. Logic Judgment System

8.5.3.3. Data Dependencies

8.5.3.4. Running Analysis

8.6. Discussion and Summary

8.6.1. Framework-Oriented Program Design

8.6.2. Robust Programming

8.6.3. Integrated Logic Architecture

8.6.4. Data Architecture Based on Semantic Approximation

8.6.5. Formal Methods for Program Semantic

Chapter 9

Super Large-Scale Interpretable Intelligent System

9.1. Basic Theory

9.1.1. Standard Specifications

9.1.2 Progressive Evolution

9.1.3. Limited Semantic and Logic Extensions

9.1.4. Large-Scale Pattern Matching

9.1.5. Instance Data System

9.2. Large Logic Model

9.2.1. Technique Roadmap

9.2.2. Global Data Pool

9.2.3. Semantic Distance Calculation and Feature Analogy Methods

9.2.4. Function Processing Nodes

9.2.5. Feature Judgment Nodes

9.2.6. Workload Balancing

9.3. Conclusion

Index

Blank Page.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

9798895302743

OCLC:

1481802616