Screen LibraryArtificial intelligence in the age of neural networks and brain computing /
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...
Saved in:
| Group Author: | ; ; ; |
|---|---|
| Published: |
Academic Press, an imprint of Elsevier,
|
| Publisher Address: | London, United Kingdom : |
| Publication Dates: | [2019] |
| Literature type: | Book |
| Language: | English |
| Subjects: | |
| Summary: |
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. -- From back cover. |
| Carrier Form: | xxv, 324 pages : illustrations ; 24 cm |
| Bibliography: | Includes bibliographical references and index. |
| ISBN: |
9780128154809 0128154802 |
| Index Number: | Q335 |
| CLC: | TP18 |
| Call Number: | TP18/A791-16 |
| Contents: |
Nature's learning rule: The Hebbian-LMS algorithm / Introduction -- ADALINE and the LMS algorithm, From the 1950s -- Unsupervised learning with Adaline, From the 1960s -- Robert Lucky's adaptive equalization, From the 1960s -- Bootstrap learning with a Sigmoidal neuron -- Bookstrap learning with a more "Biologically correct" Sigmoidal neuron -- Other clustering algorithms -- A general Hebbian-LMS algorithm -- The synapse -- Postulates of synaptic plasticity -- The postulates and the Hebbian-LMS algorithm -- Nature's Hebbian-LMS algorithm -- Conclusion -- A half century of progress toward a unified neural theory of mind and brain with applications to autonomous adaptive agents and mental disorders / Towards a unified theory of mind and brain -- A theoretical method for linking brain to mind: The method of minimal anatomies -- Revolutionary brain paradigms: Complementary computing and laminar computing -- The what and where cortical streams are complementary -- Adaptive resonance theory -- Vector associative maps for spatial representation and action -- Homologous laminar cortical circuits for all biological intelligence: Beyond Bayes -- Why a unified theory is possible: Equations, modules, and architectures -- All conscious states are resonant states -- The varieties of brain resonances and the conscious experiences that they support -- Why does resonance trigger consciousness? -- Towards autonomous adaptive intelligent agents and clinical therapies in society -- References -- Third Gen AI as human experience based expert systems / Third gen AI -- MFE gradient descent -- The brain-mind-computer trichotomy: Hermeneutic approach / Dichotomies -- Hermeneutics -- Schizophrenia: A broken hermeneutic cycle -- Toward the algorithms of neural/mental hermeneutic interpretation -- From synapses to ephapsis: Embodied cognition and wearable personal assistants / Roman Ormandy -- Neural networks and neural fields -- Ephapsis -- Embodied cognition -- Wearable personal assistants -- Evolving and spiking connectionist systems for brain-inspired artificial intelligence / From Aristotle's logic to artificial neural networks and hybrid systems -- Evolving connectionist systems (ECOS) -- Spiking neural networks (SNN) as brain-inspired ANN -- Brain-like AI systems based on SNN, NeuCube, deep learning algorithms -- Pitfalls and opportunities in the development and evaluation of artificial intelligence systems / AI development -- AI evaluation -- Variability and bias in our performance estimates -- The new AI: Basic concepts, urgent risks and opportunities in the Internet of Things / Introduction and overview -- Brief history and foundations of the deep learning revolution -- From RNNs to mouse-level computational intelligence: Next big things and beyond -- Need for new directions in understanding brain and mind -- Information technology (IT) for human survival: An urgent unmet challenge -- Theory of the brain and mind: Visions and history / Early history -- Emergence of some neural network principles -- Neural networks enter mainstream science -- Is computational neuroscience separate from neural network theory? -- Discussion -- Computers versus brains: Game is over or more to come? / AI approaches -- Metastability in cognition and in brain dynamics -- Pragmatic implementation of complementarity for new AI -- Acknowledgments -- Deep learning apporaches to electrophysiological multivariate time-series analysis / The neural network approach -- Deep architectures and learning -- Electrophysiological time-series -- Deep learning models for EEG signal processing -- Future directions of research -- Further reading -- Computational intelligence in the time of cyber-physical systems and the Internet of Things / System architecture -- Energy harvesting and management -- Learning in nonstationary environments -- Model-free fault diagnosis systems -- Cybersecurity -- Conclusions -- Multiview learning in biomedical applications / Multiview learning -- Multiview learning in bioinformatics -- Multiview learning in neuroinformatics -- Deep |