Intelligence Science: Leading the Age of Intelligence

✍ Scribed by Zhongzhi Shi

• Publisher: Elsevier
• Year: 2021
• Tongue: English
• Leaves: 617
• Category: Library

✦ Synopsis

Intelligence Science: Leading the Age of Intelligence covers the emerging scientific research on the theory and technology of intelligence, bringing together disciplines such as neuroscience, cognitive science, and artificial intelligence to study the nature of intelligence, the functional simulation of intelligent behavior, and the development of new intelligent technologies. The book presents this complex, interdisciplinary area of study in an accessible volume, introducing foundational concepts and methods, and presenting the latest trends and developments. Chapters cover the Foundations of neurophysiology, Neural computing, Mind models, Perceptual intelligence, Language cognition, Learning, Memory, Thought, Intellectual development and cognitive structure, Emotion and affect, and more. 

This volume synthesizes a very rich and complex area of research, with an aim of stimulating new lines of enquiry.

✦ Table of Contents

Title-page_2021_Intelligence-Science
Intelligence Science
Copyright_2021_Intelligence-Science
Copyright
Contents_2021_Intelligence-Science
Contents
About-the-author_2021_Intelligence-Science
About the author
Preface_2021_Intelligence-Science
Preface
Acknowledgment_2021_Intelligence-Science
Acknowledgment
Chapter-1---Introduction_2021_Intelligence-Science
1 Introduction
1.1 The Intelligence Revolution
1.2 The rise of intelligence science
1.2.1 Brain science
1.2.2 Cognitive science
1.2.3 Artificial intelligence
1.2.3.1 The formation period of artificial intelligence (1956–1976)
1.2.3.2 Symbolic intelligence period (1976–2006)
1.2.3.3 Data intelligence period (2006-present)
1.3 Ten big issues of intelligence science
1.3.1 Working mechanism of brain neural network
1.3.2 Mind modeling
1.3.3 Perceptual representation and intelligence
1.3.4 Linguistic cognition
1.3.5 Learning ability
1.3.6 Encoding and retrieval of memory
1.3.7 Thought
1.3.8 Intelligence development
1.3.9 Emotion
1.3.10 Nature of consciousness
1.4 Research contents
1.4.1 Computational neural theory
1.4.2 Cognitive mechanism
1.4.3 Knowledge engineering
1.4.4 Natural language processing
1.4.5 Intelligent robot
1.5 Research methods
1.5.1 Behavioral experiments
1.5.2 Brain imaging
1.5.3 Computational modeling
1.5.4 Neurobiological methods
1.5.5 Simulation
1.6 Prospects
References
Chapter-2---Foundation-of-neurophysiology_2021_Intelligence-Science
2 Foundation of neurophysiology
2.1 The human brain
2.2 Nervous tissues
2.2.1 Basal composition of neuron
2.2.1.1 Soma or cell body
2.2.1.2 Cell membrane
2.2.1.3 Nucleus
2.2.1.4 Cytoplasm
2.2.1.5 Process
2.2.1.6 Dendrite
2.2.1.7 Axon
2.2.2 Classification of neurons
2.2.3 Neuroglial cells
2.3 Synaptic transmission
2.3.1 Chemical synapse
2.3.1.1 Presynaptic element
2.3.1.2 Postsynaptic element
2.3.1.3 Synaptic cleft
2.3.2 Electrical synapse
2.3.3 Mechanism of synaptic transmission
2.4 Neurotransmitter
2.4.1 Acetylcholine
2.4.2 Catecholamines
2.4.2.1 Biological synthesis of catecholamines
2.4.2.2 Norepinephrine
2.4.2.3 Dopamine
2.4.3 5-hydroxytryptamine
2.4.4 Amine acid and oligopeptide
2.4.5 Nitric oxide
2.4.6 Receptor
2.5 Transmembrane signal transduction
2.5.1 Transducin
2.5.2 The second messenger
2.6 Resting membrane potential
2.7 Action potential
2.8 Ion channels
2.9 The nervous system
2.9.1 Central nervous system
2.9.2 Peripheral nervous system
2.10 Cerebral cortex
References
Chapter-3---Neural-computing_2021_Intelligence-Science
3 Neural computing
3.1 Introduction
3.2 Back-propagation learning algorithm
3.3 Adaptive resonance theory model
3.4 Bayesian linking field model
3.4.1 Elkhorn model
3.4.2 Noisy neuron firing strategy
3.4.3 Bayesian coupling of inputs
3.4.4 Competition among neurons
3.5 Recurrent neural networks
3.6 Long short-term memory
3.7 Neural field model
3.8 Neural column model
References
Chapter-4---Mind-model_2021_Intelligence-Science
4 Mind model
4.1 Mind
4.1.1 Philosophy issues of mind
4.1.1.1 Mind–body problem
4.1.1.2 Consciousness
4.1.1.3 Sensitibility
4.1.1.4 Supervenience
4.1.1.5 The language of thought
4.1.1.6 Intentionality and content theory
4.1.1.7 Mental representation
4.1.1.8 Machine mind
4.1.2 Mind modeling
4.1.2.1 To behave flexibly
4.1.2.2 Adaptive behavior
4.1.2.3 Real time
4.1.2.4 Large-scale knowledge base
4.1.2.5 Dynamic behavior
4.1.2.6 Knowledge integration
4.1.2.7 Use language
4.1.2.8 Consciousness
4.1.2.9 Learning
4.1.2.10 Development
4.1.2.11 Evolution
4.1.2.12 Brain
4.2 Turing machine
4.3 Physical symbol system
4.4 SOAR
4.4.1 Basic State, Operator And Result architecture
4.4.2 Extended version of SOAR
4.4.2.1 Working memory activation
4.4.2.2 Reinforcement learning
4.4.2.3 Semantic memory
4.4.2.4 Episodic memory
4.4.2.5 Visual imagery
4.5 ACT-R model
4.6 CAM model
4.6.1 Vision
4.6.2 Hearing
4.6.3 Perception buffer
4.6.4 Working memory
4.6.5 Short-term memory
4.6.6 Long-term memory
4.6.7 Consciousness
4.6.8 High-level cognition function
4.6.9 Action selection
4.6.10 Response output
4.7 Cognitive cycle
4.7.1 Perception phase
4.7.2 Motivation phase
4.7.3 Action planning phase
4.8 Perception, memory, and judgment model
4.8.1 Fast processing path
4.8.2 Fine processing pathway
4.8.3 Feedback processing pathway
References
Chapter-5---Perceptual-intelligence_2021_Intelligence-Science
5 Perceptual intelligence
5.1 Introduction
5.2 Perception
5.3 Representation
5.3.1 Intuitivity
5.3.2 Generality
5.3.3 Representation happens on paths of many kinds of feelings
5.3.4 Role of representation in thinking
5.3.4.1 Remembering representation
5.3.4.2 Imagining representation
5.4 Perceptual theory
5.4.1 Constructing theory
5.4.2 Gestalt theory
5.4.3 Gibson’s ecology theory
5.4.4 Topological vision theory
5.5 Vision
5.5.1 Visual pathway
5.5.2 Marr’s visual computing
5.5.2.1 The primal sketch
5.5.2.2 2.5-D sketch
5.5.2.3 Three-dimensional model
5.5.3 Image understanding
5.5.4 Face recognition
5.5.4.1 Face image acquisition and detection
5.5.4.2 Face image preprocessing
5.5.4.3 Face image feature extraction
5.5.4.4 Face image matching and recognition
5.6 Audition
5.6.1 Auditory pathway
5.6.2 Speech coding
5.6.2.1 Waveform coding
5.6.2.2 Source coding
5.6.2.3 Hybrid coding
5.7 Speech recognition and synthesis
5.7.1 Speech recognition
5.7.2 Speech synthesis
5.7.2.1 Formant synthesis
5.7.2.2 Linear prediction coding parameter syntheses
5.7.2.3 LMA vocal tract model
5.7.3 Concept to speech system
5.7.3.1 Text analysis module
5.7.3.2 Prosody prediction module
5.7.3.3 Acoustic model module
5.8 Attention
5.8.1 Attention network
5.8.2 Attention function
5.8.2.1 Orientation control
5.8.2.2 Guiding search
5.8.2.3 Keeps vigilance
5.8.3 Selective attention
5.8.3.1 Filter model
5.8.3.2 Decay model
5.8.3.3 Response selection model
5.8.3.4 Energy distribution model
5.8.4 Attention in deep learning
References
Chapter-6---Language-cognition_2021_Intelligence-Science
6 Language cognition
6.1 Introduction
6.2 Oral language
6.2.1 Perceptual analysis of language input
6.2.2 Rhythm perception
6.2.2.1 Prosodic features
6.2.2.2 Prosodic modeling
6.2.2.3 Prosodic labeling
6.2.2.4 Prosodic generation
6.2.2.5 Cognitive neuroscience of prosody generation
6.2.3 Speech production
6.3 Written language
6.3.1 Letter recognition
6.3.2 Word recognition
6.4 Chomsky’s formal grammar
6.4.1 Phrase structure grammar
6.4.2 Context-sensitive grammar
6.4.3 Context-free grammar
6.4.4 Regular grammar
6.5 Augmented transition networks
6.6 Concept dependency theory
6.7 Language understanding
6.7.1 Overview
6.7.2 Rule-based analysis method
6.7.3 Statistical model based on corpus
6.7.4 Machine learning method
6.7.4.1 Text classification
6.7.4.2 Text clustering
6.7.4.3 Case-based machine translation
6.8 Neural model of language understanding
6.8.1 Aphasia
6.8.2 Classical localization model
6.8.3 Memory-integration-control model
6.8.4 Bilingual brain functional areas
References
Chapter-7---Learning_2021_Intelligence-Science
7 Learning
7.1 Basic principle of learning
7.2 The learning theory of the behavioral school
7.2.1 Learning theory of conditioned reflex
7.2.2 Learning theory of behaviorism
7.2.3 Association learning theory
7.2.4 Operational learning theory
7.2.5 Contiguity theory of learning
7.2.6 Need reduction theory
7.3 Cognitive learning theory
7.3.1 Learning theory of Gestalt school
7.3.2 Cognitive purposive theory
7.3.3 Cognitive discovery theory
7.3.3.1 Learning is active in the process of the formation of cognitive structures
7.3.3.2 Emphasize the learning of the basic structure of discipline
7.3.3.3 The formation of cognitive structures through active discovery
7.3.4 Cognitive assimilation theory
7.3.5 Learning theory of information processing
7.3.6 Learning theory of constructivism
7.4 Humanistic learning theory
7.5 Observational learning
7.6 Introspective learning
7.6.1 Basic principles of introspection learning
7.6.2 Meta-reasoning of introspection learning
7.6.3 Failure classification
7.6.4 Case-based reasoning in the introspective process
7.7 Reinforcement learning
7.7.1 Reinforcement learning model
7.7.2 Q Learning
7.8 Deep learning
7.8.1 Introduction
7.8.2 Autoencoder
7.8.3 Restricted Boltzmann machine
7.8.4 Deep belief networks
7.8.5 Convolutional neural networks
7.8.5.1 Feed-forward propagation of the convolutional layer
7.8.5.2 Feed-forward propagation of subsampling
7.8.5.3 Error back-propagation of the subsampling layer
7.8.5.4 Error back-propagation of the convolutional layer
7.9 Cognitive machine learning
7.9.1 The emergence of learning
7.9.2 Procedural knowledge learning
7.9.3 Learning evolution
References
Chapter-8---Memory_2021_Intelligence-Science
8 Memory
8.1 Overview
8.2 Memory system
8.2.1 Sensory memory
8.2.2 Short-term memory
8.2.2.1 Classic research of Sternberg
8.2.2.2 Direct an access model
8.2.2.3 Double model
8.2.3 Long-term memory
8.3 Long-term memory
8.3.1 Semantic memory
8.3.1.1 Hierarchical network model
8.3.1.2 Spreading activation model
8.3.1.3 Human association memory
8.3.2 Episodic memory
8.3.3 Procedural memory
8.3.4 Information retrieval from long-term memory
8.3.4.1 Recognition
8.3.4.2 Recall
8.4 Working memory
8.4.1 Working memory model
8.4.2 Working memory and reasoning
8.4.3 Neural mechanism of working memory
8.5 Implicit memory
8.6 Forgetting curve
8.7 Complementary learning and memory
8.7.1 Neocortex
8.7.2 Hippocampus
8.7.3 Complementary learning system
8.8 Hierarchical temporal memory
8.8.1 Memory prediction framework
8.8.2 Cortical learning algorithm
References
Chapter-9---Thought_2021_Intelligence-Science
9 Thought
9.1 Introduction
9.2 Hierarchical model of thought
9.2.1 Abstract thought
9.2.2 Imagery thought
9.2.3 Perceptual thought
9.3 Deductive inference
9.4 Inductive inference
9.5 Abductive inference
9.6 Analogical inference
9.7 Causal inference
9.8 Commonsense reasoning
9.9 Mathematics mechanization
References
Chapter-10---Intelligence-development_2021_Intelligence-Science
10 Intelligence development
10.1 Intelligence
10.2 Intelligence test
10.3 Cognitive structure
10.3.1 Piaget’s schema theory
10.3.2 Gestalt’s insight theory
10.3.3 Tolman’s cognitive map theory
10.3.4 Bruner’s theory of classification
10.3.5 Ausubel’s theory of cognitive assimilation
10.4 Intelligence development based on operation
10.4.1 Schema
10.4.2 Stages of children’s intelligence development
10.4.2.1 Sensorimotor period (0–2 years old)
10.4.2.2 Preoperational stage (2–7 years)
10.4.2.2.1 Preconceptual stage (2–4 years)
10.4.2.2.2 Intuitive stage (4–7 years)
10.4.2.3 Concrete operational stage (7–11 years)
10.4.2.4 Formal operational stage (12∼15 years)
10.5 Intelligence development based on morphism category theory
10.5.1 Category theory
10.5.2 Topos
10.5.3 Morphisms and categories
10.6 Psychological logic
10.6.1 Combined system
10.6.2 INRC quaternion group structure
10.7 Artificial system of intelligence development
References
Chapter-11---Emotion-intelligence_2021_Intelligence-Science
11 Emotion intelligence
11.1 Introduction
11.1.1 Difference lies in requirement
11.1.2 Difference lies in occurrence time
11.1.3 Difference lies in reaction characteristics
11.2 Emotion theory
11.2.1 James-Lange’s theory of emotion
11.2.2 Cognitive theory of emotion
11.2.3 Basic emotions theory
11.2.4 Dimension theory
11.2.5 Emotional semantic network theory
11.2.6 Beck’s schema theory
11.3 Emotional model
11.3.1 Mathematical model
11.3.2 Cognitive model
11.3.3 Emotion model based on Markov decision process
11.4 Emotional quotient
11.5 Affective computing
11.5.1 Facial expressions
11.5.2 Gesture change
11.5.3 Speech understanding
11.5.4 Multimodal affective computing
11.5.5 Affective computing and personalized service
11.5.6 The influence of affective understanding
11.6 Neural basis of emotion
11.6.1 Emotion pathway
11.6.2 Papez loop
11.6.3 Cognitive neuroscience
References
Chapter-12---Consciousness_2021_Intelligence-Science
12 Consciousness
12.1 Overview
12.1.1 Base elements of consciousness
12.1.2 The attribute of consciousness
12.2 Global workspace theory
12.2.1 The theater of consciousness
12.2.2 Global workspace model
12.3 Reductionism
12.4 Theory of neuronal group selection
12.5 Quantum theories
12.6 Information integration theory
12.7 Consciousness system in CAM
12.7.1 Awareness module
12.7.2 Attention module
12.7.3 Global workspace module
12.7.4 Motivation module
12.7.5 Metacognition module
12.7.6 Introspective learning module
12.8 Conscious Turing machine
References
Chapter-13---Brain-computer-integration_2021_Intelligence-Science
13 Brain–computer integration
13.1 Overview
13.2 Modules of the brain–computer interface
13.3 Electroencephalography signal analysis
13.3.1 Electroencephalography signal sorting
13.3.2 Electroencephalography signal analytical method
13.4 Brain–computer interface technology
13.4.1 Visual-evoked potential
13.4.2 Event-related potential
13.4.2.1 P300 potential
13.4.2.2 Event-related desynchronization
13.4.3 Spontaneous electroencephalography for action training
13.4.4 Self-regulation of steady-state visual-evoked professional
13.5 P300 brain–computer interface system
13.5.1 Architecture
13.5.2 Visual elicitor subsystem
13.5.3 Electroencephalography acquisition subsystem
13.5.4 Electroencephalography analysis subsystem
13.6 ABGP agent
13.7 Key technologies of brain–computer integration
13.7.1 Cognitive model of brain–computer integration
13.7.2 Environment awareness
13.7.3 Autonomous reasoning
13.7.4 Collaborative decision-making
13.7.5 Simulation experiment
References
Chapter-14---Brain-like-intelligence_2021_Intelligence-Science
14 Brain-like intelligence
14.1 Introduction
14.2 Blue Brain Project
14.2.1 Brain neural network
14.2.2 Cerebral cortex model
14.2.3 Super computational simulation
14.3 Human Brain Project
14.3.1 Research contents of the project
14.3.1.1 Data
14.3.1.2 Theory
14.3.1.3 The technology platform of information and communication
14.3.1.4 Applications
14.3.1.5 Social ethics
14.3.2 Timing plasticity of peak potential
14.3.3 Unified brain model
14.4 Brain research in the United States
14.4.1 Human connectome project
14.4.2 MoNETA
14.4.3 Neurocore chip
14.5 China Brain Project
14.5.1 Brain map and connectome
14.5.2 General intelligent platform
14.5.3 Artificial intelligence chip
14.5.4 Tianjic chip
14.5.5 Decoupled NEUTRAMS
14.6 Neuromorphic chip
14.6.1 The development history
14.6.2 IBM’s TrueNorth neuromorphic system
14.6.3 British SpiNNaker
14.7 Memristor
14.7.1 Overview
14.7.2 In-memory computing
14.8 Development roadmap of intelligence science
14.8.1 Elementary brain-like computing
14.8.1.1 Natural language processing
14.8.1.2 Image semantics generation
14.8.1.3 Speech recognition
14.8.1.4 Language cognitive
14.8.2 Advanced brain-like computing
14.8.2.1 The perception, assessment, and presentation of emotion
14.8.2.2 Promote mood in the process of thinking
14.8.2.3 The understanding and feeling of mood
14.8.2.4 Adjust maturely to emotion
14.8.2.5 Maintain the harmonious interpersonal relationship
14.8.2.6 Deal with frustration
14.8.3 Super-brain computing
14.8.3.1 High intelligence
14.8.3.2 High-performance
14.8.3.3 Low energy consumption
14.8.3.4 High fault-tolerance
14.8.3.5 All-consciousness
References
Index_2021_Intelligence-Science
Index