Artificial intelligence in the age of neural networks and brain computing / / edited by Robert Kozma [and three others]

• Pubblicazione: London, United Kingdom : , : Academic Press, An imprint of Elsevier, , [2019]
• Descrizione fisica: 1 online resource (352 pages)
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence; Neural networks (Computer science)
• Persona (resp. second.): KozmaRobert
• Nota di contenuto: Front Cover -- Artificial Intelligence in the Age of Neural Networks and Brain Computing -- Artificial Intelligence in the Age of Neural Networks and Brain Computing -- Copyright -- Contents -- List of Contributors -- Editors' Brief Biographies -- Introduction -- 1 - Nature's Learning Rule: The Hebbian-LMS Algorithm -- 1. INTRODUCTION -- 2. ADALINE AND THE LMS ALGORITHM, FROM THE 1950S -- 3. UNSUPERVISED LEARNING WITH ADALINE, FROM THE 1960S -- 4. ROBERT LUCKY'S ADAPTIVE EQUALIZATION, FROM THE 1960S -- 5. BOOTSTRAP LEARNING WITH A SIGMOIDAL NEURON -- 6. BOOTSTRAP LEARNING WITH A MORE "BIOLOGICALLY CORRECT" SIGMOIDAL NEURON -- 6.1 TRAINING A NETWORK OF HEBBIAN-LMS NEURONS -- 7. OTHER CLUSTERING ALGORITHMS -- 7.1 K-MEANS CLUSTERING -- 7.2 EXPECTATION-MAXIMIZATION ALGORITHM -- 7.3 DENSITY-BASED SPATIAL CLUSTERING OF APPLICATION WITH NOISE ALGORITHM -- 7.4 COMPARISON BETWEEN CLUSTERING ALGORITHMS -- 8. A GENERAL HEBBIAN-LMS ALGORITHM -- 9. THE SYNAPSE -- 10. POSTULATES OF SYNAPTIC PLASTICITY -- 11. THE POSTULATES AND THE HEBBIAN-LMS ALGORITHM -- 12. NATURE'S HEBBIAN-LMS ALGORITHM -- 13. CONCLUSION -- APPENDIX: TRAINABLE NEURAL NETWORK INCORPORATING HEBBIAN-LMS LEARNING -- ACKNOWLEDGMENTS -- REFERENCES -- 2 - A Half Century of Progress Toward a Unified Neural Theory of Mind and Brain With Applications to Autonomous Ada ... -- 1. TOWARDS A UNIFIED THEORY OF MIND AND BRAIN -- 2. A THEORETICAL METHOD FOR LINKING BRAIN TO MIND: THE METHOD OF MINIMAL ANATOMIES -- 3. REVOLUTIONARY BRAIN PARADIGMS: COMPLEMENTARY COMPUTING AND LAMINAR COMPUTING -- 4. THE WHAT AND WHERE CORTICAL STREAMS ARE COMPLEMENTARY -- 5. ADAPTIVE RESONANCE THEORY -- 6. VECTOR ASSOCIATIVE MAPS FOR SPATIAL REPRESENTATION AND ACTION -- 7. HOMOLOGOUS LAMINAR CORTICAL CIRCUITS FOR ALL BIOLOGICAL INTELLIGENCE: BEYOND BAYES. ; 8. WHY A UNIFIED THEORY IS POSSIBLE: EQUATIONS, MODULES, AND ARCHITECTURES -- 9. ALL CONSCIOUS STATES ARE RESONANT STATES -- 10. THE VARIETIES OF BRAIN RESONANCES AND THE CONSCIOUS EXPERIENCES THAT THEY SUPPORT -- 11. WHY DOES RESONANCE TRIGGER CONSCIOUSNESS? -- 12. TOWARDS AUTONOMOUS ADAPTIVE INTELLIGENT AGENTS AND CLINICAL THERAPIES IN SOCIETY -- REFERENCES -- 3 - Third Gen AI as Human Experience Based Expert Systems -- 1. INTRODUCTION -- 2. THIRD GEN AI -- 2.1 MAXWELL-BOLTZMANN HOMEOSTASIS [8] -- 2.2 THE INVERSE IS CONVOLUTION NEURAL NETWORKS -- 2.3 FUZZY MEMBERSHIP FUNCTION (FMF AND DATA BASIS) -- 3. MFE GRADIENT DESCENT -- 3.1 UNSUPERVISED LEARNING RULE -- 4. CONCLUSION -- ACKNOWLEDGMENT -- REFERENCES -- FURTHER READING -- 4 - The Brain-Mind-Computer Trichotomy: Hermeneutic Approach -- 1. DICHOTOMIES -- 1.1 THE BRAIN-MIND PROBLEM -- 1.2 THE BRAIN-COMPUTER ANALOGY/DISANALOGY -- 1.3 THE COMPUTATIONAL THEORY OF MIND -- 2. HERMENEUTICS -- 2.1 SECOND-ORDER CYBERNETICS -- 2.2 HERMENEUTICS OF THE BRAIN -- 2.3 THE BRAIN AS A HERMENEUTIC DEVICE -- 2.4 NEURAL HERMENEUTICS -- 3. SCHIZOPHRENIA: A BROKEN HERMENEUTIC CYCLE -- 3.1 HERMENEUTICS, COGNITIVE SCIENCE, SCHIZOPHRENIA -- 4. TOWARD THE ALGORITHMS OF NEURAL/MENTAL HERMENEUTICS -- 4.1 UNDERSTANDING SITUATIONS: NEEDS HERMENEUTIC INTERPRETATION -- ACKNOWLEDGMENTS -- REFERENCES -- FURTHER READING -- 5 - From Synapses to Ephapsis: Embodied Cognition and Wearable Personal Assistants -- 1. NEURAL NETWORKS AND NEURAL FIELDS -- 2. EPHAPSIS -- 3. EMBODIED COGNITION -- 4. WEARABLE PERSONAL ASSISTANTS -- REFERENCES -- 6 - Evolving and Spiking Connectionist Systems for Brain-Inspired Artificial Intelligence -- 1. FROM ARISTOTLE'S LOGIC TO ARTIFICIAL NEURAL NETWORKS AND HYBRID SYSTEMS -- 1.1 ARISTOTLE'S LOGIC AND RULE-BASED SYSTEMS FOR KNOWLEDGE REPRESENTATION AND REASONING. ; 1.2 FUZZY LOGIC AND FUZZY RULE-BASED SYSTEMS -- 1.3 CLASSICAL ARTIFICIAL NEURAL NETWORKS (ANN) -- 1.4 INTEGRATING ANN WITH RULE-BASED SYSTEMS: HYBRID CONNECTIONIST SYSTEMS -- 1.5 EVOLUTIONARY COMPUTATION (EC): LEARNING PARAMETER VALUES OF ANN THROUGH EVOLUTION OF INDIVIDUAL MODELS AS PART OF POPULATIO ... -- 2. EVOLVING CONNECTIONIST SYSTEMS (ECOS) -- 2.1 PRINCIPLES OF ECOS -- 2.2 ECOS REALIZATIONS AND AI APPLICATIONS -- 3. SPIKING NEURAL NETWORKS (SNN) AS BRAIN-INSPIRED ANN -- 3.1 MAIN PRINCIPLES, METHODS, AND EXAMPLES OF SNN AND EVOLVING SNN (ESNN) -- 3.2 APPLICATIONS AND IMPLEMENTATIONS OF SNN FOR AI -- 4. BRAIN-LIKE AI SYSTEMS BASED ON SNN. NEUCUBE. DEEP LEARNING ALGORITHMS -- 4.1 BRAIN-LIKE AI SYSTEMS. NEUCUBE -- 4.2 DEEP LEARNING AND DEEP KNOWLEDGE REPRESENTATION IN NEUCUBE SNN MODELS: METHODS AND AI APPLICATIONS [6] -- 4.2.1 Supervised Learning for Classification of Learned Patterns in a SNN Model -- 4.2.2 Semisupervised Learning -- 5. CONCLUSION -- ACKNOWLEDGMENT -- REFERENCES -- 7 - Pitfalls and Opportunities in the Development and Evaluation of Artificial Intelligence Systems -- 1. INTRODUCTION -- 2. AI DEVELOPMENT -- 2.1 OUR DATA ARE CRAP -- 2.2 OUR ALGORITHM IS CRAP -- 3. AI EVALUATION -- 3.1 USE OF DATA -- 3.2 PERFORMANCE MEASURES -- 3.3 DECISION THRESHOLDS -- 4. VARIABILITY AND BIAS IN OUR PERFORMANCE ESTIMATES -- 5. CONCLUSION -- ACKNOWLEDGMENT -- REFERENCES -- 8 - The New AI: Basic Concepts, and Urgent Risks and Opportunities in the Internet of Things -- 1. INTRODUCTION AND OVERVIEW -- 1.1 DEEP LEARNING AND NEURAL NETWORKS BEFORE 2009-11 -- 1.2 THE DEEP LEARNING CULTURAL REVOLUTION AND NEW OPPORTUNITIES -- 1.3 NEED AND OPPORTUNITY FOR A DEEP LEARNING REVOLUTION IN NEUROSCIENCE -- 1.4 RISKS OF HUMAN EXTINCTION, NEED FOR NEW PARADIGM FOR INTERNET OF THINGS -- 2. BRIEF HISTORY AND FOUNDATIONS OF THE DEEP LEARNING REVOLUTION. ; 2.1 OVERVIEW OF THE CURRENT LANDSCAPE -- 2.2 HOW THE DEEP REVOLUTION ACTUALLY HAPPENED -- 2.3 BACKPROPAGATION: THE FOUNDATION WHICH MADE THIS POSSIBLE -- 2.4 CONNS, 3 LAYERS, AND AUTOENCODERS: THE THREE MAIN TOOLS OF TODAY'S DEEP LEARNING -- 3. FROM RNNS TO MOUSE-LEVEL COMPUTATIONAL INTELLIGENCE: NEXT BIG THINGS AND BEYOND -- 3.1 TWO TYPES OF RECURRENT NEURAL NETWORK -- 3.2 DEEP VERSUS BROAD: A FEW PRACTICAL ISSUES -- 3.3 ROADMAP FOR MOUSE-LEVEL COMPUTATIONAL INTELLIGENCE (MLCI) -- 3.4 EMERGING NEW HARDWARE TO ENHANCE CAPABILITY BY ORDERS OF MAGNITUDE -- 4. NEED FOR NEW DIRECTIONS IN UNDERSTANDING BRAIN AND MIND -- 4.1 TOWARD A CULTURAL REVOLUTION IN HARD NEUROSCIENCE -- 4.2 FROM MOUSE BRAIN TO HUMAN MIND: PERSONAL VIEWS OF THE LARGER PICTURE -- 5. INFORMATION TECHNOLOGY (IT) FOR HUMAN SURVIVAL: AN URGENT UNMET CHALLENGE -- 5.1 EXAMPLES OF THE THREAT FROM ARTIFICIAL STUPIDITY -- 5.2 CYBER AND EMP THREATS TO THE POWER GRID -- 5.3 THREATS FROM UNDEREMPLOYMENT OF HUMANS -- 5.4 PRELIMINARY VISION OF THE OVERALL PROBLEM, AND OF THE WAY OUT -- REFERENCES -- 9 - Theory of the Brain and Mind: Visions and History -- 1. EARLY HISTORY -- 2. EMERGENCE OF SOME NEURAL NETWORK PRINCIPLES -- 3. NEURAL NETWORKS ENTER MAINSTREAM SCIENCE -- 4. IS COMPUTATIONAL NEUROSCIENCE SEPARATE FROM NEURAL NETWORK THEORY? -- 5. DISCUSSION -- REFERENCES -- 10 - Computers Versus Brains: Game Is Over or More to Come? -- 1. INTRODUCTION -- 2. AI APPROACHES -- 3. METASTABILITY IN COGNITION AND IN BRAIN DYNAMICS -- 4. MULTISTABILITY IN PHYSICS AND BIOLOGY -- 5. PRAGMATIC IMPLEMENTATION OF COMPLEMENTARITY FOR NEW AI -- ACKNOWLEDGMENTS -- REFERENCES -- 11 - Deep Learning Approaches to Electrophysiological Multivariate Time-Series Analysis∗∗ -- 1. INTRODUCTION -- 2. THE NEURAL NETWORK APPROACH -- 3. DEEP ARCHITECTURES AND LEARNING -- 3.1 DEEP BELIEF NETWORKS -- 3.2 STACKED AUTOENCODERS. ; 3.3 CONVOLUTIONAL NEURAL NETWORKS -- 4. ELECTROPHYSIOLOGICAL TIME-SERIES -- 4.1 MULTICHANNEL NEUROPHYSIOLOGICAL MEASUREMENTS OF THE ACTIVITY OF THE BRAIN -- 4.2 ELECTROENCEPHALOGRAPHY (EEG) -- 4.3 HIGH-DENSITY ELECTROENCEPHALOGRAPHY -- 4.4 MAGNETOENCEPHALOGRAPHY -- 5. DEEP LEARNING MODELS FOR EEG SIGNAL PROCESSING -- 5.1 STACKED AUTOENCODERS -- 5.2 SUMMARY OF THE PROPOSED METHOD FOR EEG CLASSIFICATION -- 5.3 DEEP CONVOLUTIONAL NEURAL NETWORKS -- 5.4 OTHER DL APPROACHES -- 6. FUTURE DIRECTIONS OF RESEARCH -- 6.1 DL INTERPRETABILITY -- 6.2 ADVANCED LEARNING APPROACHES IN DL -- 6.3 ROBUSTNESS OF DL NETWORKS -- 7. CONCLUSIONS -- REFERENCES -- FURTHER READING -- 12 - Computational Intelligence in the Time of Cyber-Physical Systems and the Internet of Things -- 1. INTRODUCTION -- 2. SYSTEM ARCHITECTURE -- 3. ENERGY HARVESTING AND MANAGEMENT -- 3.1 ENERGY HARVESTING -- 3.2 ENERGY MANAGEMENT AND RESEARCH CHALLENGES -- 4. LEARNING IN NONSTATIONARY ENVIRONMENTS -- 4.1 PASSIVE ADAPTATION MODALITY -- 4.2 ACTIVE ADAPTATION MODALITY -- 4.3 RESEARCH CHALLENGES -- 5. MODEL-FREE FAULT DIAGNOSIS SYSTEMS -- 5.1 MODEL-FREE FAULT DIAGNOSIS SYSTEMS -- 5.2 RESEARCH CHALLENGES -- 6. CYBERSECURITY -- 6.1 HOW CAN CPS AND IOT BE PROTECTED FROM CYBERATTACKS? -- 6.2 CASE STUDY: DARKNET ANALYSIS TO CAPTURE MALICIOUS CYBERATTACK BEHAVIORS -- 7. CONCLUSIONS -- ACKNOWLEDGMENTS -- REFERENCES -- 13 - Multiview Learning in Biomedical Applications -- 1. INTRODUCTION -- 2. MULTIVIEW LEARNING -- 2.1 INTEGRATION STAGE -- 2.2 TYPE OF DATA -- 2.3 TYPES OF ANALYSIS -- 3. MULTIVIEW LEARNING IN BIOINFORMATICS -- 3.1 PATIENT SUBTYPING -- 3.2 DRUG REPOSITIONING -- 4. MULTIVIEW LEARNING IN NEUROINFORMATICS -- 4.1 AUTOMATED DIAGNOSIS SUPPORT TOOLS FOR NEURODEGENERATIVE DISORDERS -- 4.2 MULTIMODAL BRAIN PARCELLATION -- 5. DEEP MULTIMODAL FEATURE LEARNING. ; 5.1 DEEP LEARNING APPLICATION TO PREDICT PATIENT'S SURVIVAL.
• Sommario/riassunto: Artificial Intelligence in the Age of Neural Networks and Brain Computing is the comprehensive guide for neural network advances in artificial intelligence (AI). It covers the major, basic ideas of "brain-like computing" behind AI, providing a framework to deep learning and launching novel and intriguing paradigms as possible future alternatives. Following an introduction, initial chapters discuss revolutionary new brain-mind approaches alternative to deep learning, the brain-mind-computer trichotomy, pitfalls and opportunities in the development of AI systems. Subsequent chapters explore a deep learning approach to electrophysiological multivariate time series analysis, multiview learning in biomedical applications, and the evolution of deep neural networks. This is an essential companion to researchers, engineers, advance AI practitioners, postdoctoral students in computational intelligence and neural engineering, and the technically oriented public. It provides access to the latest up-to-date knowledge from top, global experts working on theory and cutting-edge applications in signal processing, speech recognition, games, adaptive control, and decision-making. --
• Titolo autorizzato: Artificial intelligence in the age of neural networks and brain computing
• ISBN: 0-12-816250-3; 0-12-815480-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910583305603321
• Lo trovi qui: Univ. Federico II