Interdisciplinary Evolution of the Machine Brain: Vision, Touch & Mind (Research on Intelligent Manufacturing)

✍ Scribed by Wenfeng Wang, Hengjin Cai, Xiangyang Deng, Chenguang Lu, Limin Zhang

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 154
• Category: Library

✦ Synopsis

This book seeks to interpret connections between the machine brain, mind and vision in an alternative way and promote future research into the Interdisciplinary Evolution of Machine Brain (IEMB). It gathers novel research on IEMB, and offers readers a step-by-step introduction to the theory and algorithms involved, including data-driven approaches in machine learning, monitoring and understanding visual environments, using process-based perception to expand insights, mechanical manufacturing for remote sensing, reconciled connections between the machine brain, mind and vision, and the interdisciplinary evolution of machine intelligence.

This book is intended for researchers, graduate students and engineers in the fields of robotics, Artificial Intelligence and brain science, as well as anyone who wishes to learn the core theory, principles, methods, algorithms, and applications of IEMB.

✦ Table of Contents

Preface
Contents
1 Introduction of Cognition Science
1.1 Background
1.2 Preliminaries and Basic Concepts
1.2.1 Region to Collect Geospatial Data
1.2.2 Definition of “Eigenobjects”
1.2.3 Attempts to Understand Machine Minds
1.3 Perspective Simulation and Characterization
1.3.1 Eigenobjects Detecting and Tracking
1.3.2 Necessity to Introduce GeoADAS
1.3.3 A Perspective Characterization of Ambulanceye
1.4 Theoretical Framework of Machine Cognition
1.5 Outline of the Book
References
2 Cognitive Computation and Systems
2.1 Background
2.2 Preliminaries for Cognitive Computation
2.2.1 Description of EEG Dataset
2.2.2 Construction of the Cognitive System
2.3 Cognitive Computation Processes
2.3.1 Process of the Convolution Operation
2.3.2 Layers of Batch Normalization
2.3.3 Feature Fusion and Classification
2.4 Machine Cognition Processes
2.4.1 Training of the Cognitive System
2.4.2 Evaluation of the CNN Model
2.4.3 Treatment of the Statistical Uncertainty
2.5 Practical Applications of the Cognitive System
2.5.1 Configuration of the Cognitive Models
2.5.2 Models Performance and Evaluation
2.5.3 Comparisons with Other Cognitive Systems
References
3 Data Mining in Environments Sensing
3.1 Introduction
3.2 A Parallel Framework for Feature Extraction
3.2.1 Welch’s Method
3.2.2 Serial Algorithm of Welch Method
3.3 Proposed Parallel Framework of Welch Method
3.3.1 Program Structure
3.3.2 Distribution of Tasks
3.4 Experimental Results and Analysis
3.4.1 Description of the Dataset
3.4.2 Testing Method and Environment
3.4.3 Experimental Results
3.5 Data Mining in Environments Sensing
3.5.1 Description of the Considered Problem
3.5.2 Problem Formulation and Learning Processes
3.5.3 Process of Reinforcement Learning
3.5.4 Results Discussion and Uncertainty Analyses
References
4 Pattern Analysis and Scene Understanding
4.1 Introduction
4.2 Background
4.2.1 Statistical Probability, Logical Probability, Shannon’s Channel, and Semantic Channel
4.2.2 To Review Popular Confirmation Measures
4.2.3 To Distinguish a Major Premise’s Evidence and Its Consequent’s Evidence
4.2.4 Incremental Confirmation or Absolute Confirmation?
4.2.5 The Semantic Channel and the Degree of Belief of Medical Tests
4.2.6 Semantic Information Formulas and the Nicod–Fisher Criterion
4.2.7 Selecting Hypotheses and Confirming Rules: Two Tasks from the View of Statistical Learning
4.3 Two Novel Confirmation Measures
4.3.1 To Derive Channel Confirmation Measure b
4.3.2 To Derive Prediction Confirmation Measure c
4.3.3 Converse Channel/Prediction Confirmation Measures b(h → e) and c(h → e)
4.3.4 Eight Confirmation Formulas for Different Antecedents and Consequents
4.3.5 Relationship Between Measures b and F
4.3.6 Relationships Between Prediction Confirmation Measures and Some Medical Test’s Indexes
4.4 Pattern Analysis: A Practical Application
4.4.1 Using Three Examples to Compare Various Confirmation Measures
4.4.2 Using Measures b to Explain Why and How CT Is also Used to Test COVID-19
4.4.3 How Various Confirmation Measures Are Affected by Increments Δa and Δd
4.5 Scene Understanding: How to Further Develop Our Theory
4.5.1 To Clarify the Raven Paradox
4.5.2 About Incremental Confirmation and Absolute Confirmation
4.5.3 Is Hypothesis Symmetry or Consequent Symmetry Desirable?
4.5.4 About Bayesian Confirmation and Likelihoodist Confirmation
4.5.5 About the Certainty Factor for Probabilistic Expert Systems
4.5.6 How Confirmation Measures F, b, and c Are Compatible with Popper’s Falsification Thought
4.6 Concluded Remarks and Outstanding Questions
References
5 Reconciled Interpretation of Vision, Touch and Minds
5.1 Background
5.2 Preliminaries of Cognitive Computation
5.2.1 Evolution Stages of the Machine Brain
5.2.2 Cognitive Systems in GeoAI for Unmanned Driving
5.2.3 The Robot Path Planning (RPP) Problem
5.3 The Minds Brain Hypothesis
5.3.1 From Vision to Vision-Minds
5.3.2 Understanding the Minds Brain Hypothesis
5.3.3 The Traveling Salesman Problem (TSP)
5.4 Cognitive Computation and Machine Minds
5.4.1 Supplementary Explanation of Machine Minds
5.4.2 From Machine Learning to Machine Understanding
5.4.3 The Vision-Minds Brain Hypothesis and Associated Cognitive Models
5.5 Reconciled Interpretation of Vision, Touch and Minds
5.5.1 Improvements of the Cognitive System
5.5.2 Further Interpretation of the Vision-Minds Hypothesis
5.5.3 Extension of Boundaries and the Skin Brain Hypothesis
5.6 Simulation of the Transponder Transmission System
5.6.1 Development History of Transponders Transmission System
5.6.2 Analysis of Uplink Signal of Transmitter
5.6.3 Constructing the Simulation System on Transponder Transmission
References
6 Interdisciplinary Evolution of the Machine Brain
6.1 Background
6.2 Practical Multi-modules Integration
6.2.1 Scheme for Integration
6.2.2 Vision and Auditory Integration
6.3 Practical Multi-model Fusion
6.3.1 Sensor Layer Fusion
6.3.2 Feature Layer Fusion
6.3.3 Knowledge Layer Fusion
6.3.4 Decision Layer Fusion
6.4 Applications in a Robot System
6.4.1 Deep Vision System
6.4.2 Underwater Robot System
6.4.3 Integration Cognition with Behavior Trees
6.5 Application of Computer in Mixed Reality Technology
6.5.1 Development Trend of Hybrid Reality Technology
6.5.2 Characteristics of Key Technologies in Hybrid Reality
6.5.3 Application of Computer in Hybrid Reality Technology
References