Artificial Intelligence in the Age of Neural Networks and Brain Computing

2nd Edition - October 10, 2023
Editors: Robert Kozma, Cesare Alippi, Yoonsuck Choe, Francesco Carlo Morabito
Language: English
Paperback ISBN:
9 7 8 - 0 - 3 2 3 - 9 6 1 0 4 - 2
eBook ISBN:
9 7 8 - 0 - 3 2 3 - 9 5 8 1 6 - 5

Artificial Intelligence in the Age of Neural Networks and Brain Computing, Second Edition demonstrates that present disruptive implications and applications of AI is a developme… Read more

Purchase options

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

Artificial Intelligence in the Age of Neural Networks and Brain Computing, Second Edition demonstrates that present disruptive implications and applications of AI is a development of the unique attributes of neural networks, mainly machine learning, distributed architectures, massive parallel processing, black-box inference, intrinsic nonlinearity, and smart autonomous search engines. The book covers the major basic ideas of "brain-like computing" behind AI, provides a framework to deep learning, and launches novel and intriguing paradigms as possible future alternatives.

The present success of AI-based commercial products proposed by top industry leaders, such as Google, IBM, Microsoft, Intel, and Amazon, can be interpreted using the perspective presented in this book by viewing the co-existence of a successful synergism among what is referred to as computational intelligence, natural intelligence, brain computing, and neural engineering. The new edition has been updated to include major new advances in the field, including many new chapters.

Cover image
Title page
Table of Contents
Copyright
Contributors
Editors' brief biographies
Introduction
1: Advances in AI, neural networks, and brain computing: An introduction
Abstract
1: Introduction
Part 1: Fundamentals of neural networks and brain computing
2: Nature's learning rule: The Hebbian-LMS algorithm
Abstract
Acknowledgments
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
7: Other 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
Chapter postscript
References
Further reading
3: A half century of progress toward a unified neural theory of mind and brain with applications to autonomous adaptive agents and mental disorders
Abstract
1: Toward 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: Toward autonomous adaptive intelligent agents and clinical therapies in society
References
4: Meaning versus information, prediction versus memory, and question versus answer
Abstract
Acknowledgments
1: Introduction
2: Meaning vs information
3: Prediction vs memory
4: Question vs answer
5: Discussion
6: Conclusion
References
5: The brain-mind-computer trichotomy: Hermeneutic approach
Abstract
Acknowledgments
1: Dichotomies
2: Hermeneutics
3: Schizophrenia: A broken hermeneutic cycle
4: Toward the algorithms of neural/mental hermeneutics
References
Further reading
Part 2: Brain-inspired AI systems
6: The new AI: Basic concepts, and urgent risks and opportunities in the internet of things
Abstract
1: Introduction and overview
2: Brief history and foundations of the deep learning revolution
3: From RNNs to mouse-level computational intelligence: Next big things and beyond
4: Need for new directions in understanding brain and mind
5: Information technology (IT) for human survival: An urgent unmet challenge
6: From deep learning to the future: How to build and use true quantum artificial general intelligence
Appendix: Neural network revolutions, past and future: From BP (neural and fuzzy) to quantum artificial general intelligence (QAGI)
References
7: Computers versus brains: Challenges of sustainable artificial and biological intelligence
Abstract
Acknowledgments
1: The dream of creating artificial intelligence
2: What can AI learn from biological intelligence (BI)?
3: Always at the edge—The miracle of life and intelligence
4: Implementation of complementarity for new AI
5: Conclusion: Sustainable AI to support humanity
References
8: Brain-inspired evolving and spiking connectionist systems
Abstract
Acknowledgment
1: The historic merge of artificial neural networks and fuzzy logic
2: Evolving connectionist systems (ECOS)
3: Spiking neural networks (SNNs)
4: Brain-inspired SNN. NeuCube
5: What role can evolutionary computation (EC) methods play for life-long learning in evolving connectionist systems (ECOS)?
6: Conclusion
References
9: Pitfalls and opportunities in the development and evaluation of artificial intelligence systems
Abstract
Acknowledgment
1: Introduction
2: AI development
3: AI evaluation
4: Variability and bias in our performance estimates
5: Conclusion
References
10: Theory of the brain and mind: Visions and history
Abstract
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
11: From synapses to ephapsis: Embodied cognition and wearable personal assistants
Abstract
1: Neural networks and neural fields
2: Ephapsis
3: Embodied cognition
4: Wearable personal assistants
References
Part 3: Cutting-edge developments in deep learning and intelligent systems
12: Explainable deep learning to information extraction in diagnostics and electrophysiological multivariate time series
Abstract
1: Introduction
2: The neural network approach
3: Deep architectures and learning
4: Electrophysiological time series
5: Deep learning models for EEG signal processing
6: Future directions of research
7: Conclusions
References
13: Computational intelligence in cyber-physical systems and the Internet of Things
Abstract
Acknowledgment
1: Introduction
2: System architecture
3: Energy harvesting and management
4: Learning in nonstationary environments
5: Model-free fault diagnosis systems
6: Cyber-security
7: Conclusions
References
14: Evolving deep neural networks
Abstract
1: Introduction
2: Background and related work
3: Evolution of deep learning architectures
4: Evolution of LSTM architectures
5: Application case study: Image captioning for the blind
6: Discussion and future work
7: Conclusions
References
15: Evolving GAN formulations for higher-quality image synthesis
Abstract
1: Introduction
2: Variations of GAN architectures
3: Evolution of loss functions
4: The TaylorGAN approach
5: Experimental setup
6: Results
7: Discussion and future work
8: Conclusions
References
16: Multiview learning in biomedical applications
Abstract
1: Introduction
2: Multiview learning
3: Multiview learning in bioinformatics
4: Multiview learning in neuroinformatics
5: Deep multimodal feature learning
6: Conclusions
References
17: Emergence of tool construction and tool use through hierarchical reinforcement learning
Abstract
Acknowledgments
1: Introduction
2: Background and related works
3: Approach
4: Experiments and results
5: Discussion and conclusion
References
18: A Lagrangian framework for learning in graph neural networks
Abstract
Acknowledgments
1: Introduction
2: Constraint-based models of neural networks
3: Local propagation in graph neural networks
4: Conclusions
References
Index

Robert Kozma

Dr. Robert Kozma Ph.D (Fellow of IEEE, Fellow of INNS) is Professor of Mathematical Sciences, the University of Memphis, and Professor of Computer Science at University of Massachusetts Amherst. He holds a PhD in Physics and 2 MSc degrees in Mathematics and Power Engineering. His research is focused on computational neurodynamics, large-scale brain networks, and applying biologically motivated and cognitive principles for the development of intelligent systems. Previous affiliations include visiting positions at NASA/JPL, Sarnoff Co., Princeton, NJ; Lawrence Berkeley Laboratory (LBL); AFRL, Dayton, OH; joint EECS/Neurobiology appointment at UC Berkeley; Associate Professor at Tohoku University, Sendai, Japan; Lecturer at Otago University, Dunedin, New Zealand. His research career started over 35 years ago as a research fellow at the Hungarian Academy of Sciences, Budapest, Hungary. He has published 8 books, 350+ papers, has 3 patent submissions. His research has been supported by NSF, NASA, JPL, AFRL, DARPA, FedEx, and by other agencies. He is President of INNS (2017-2018), serves on the Board of IEEE SMC Society (2016-2018); has served on the AdCom of the IEEE Computational Intelligence Society (2009-2012) and the Board of Governors of the International Neural Network Society (2007-2012). He has been General Chair of IJCNN2009, Atlanta, USA. He is Associate Editor of Neural Networks, Neurocomputing, Cognitive Systems Research, and Cognitive Neurodynamics. Dr. Kozma is the recipient of the INNS Gabor Award.

Affiliations and expertise

Department of Mathematics, University of Memphis, Memphis, TN, United States; Research and Innovation Center, Óbuda University, Budapest, Hungary

Cesare Alippi

Dr. Cesare Alippi Ph.D received his degree in electronic engineering cum laude and his PhD from Politecnico di Milano, Italy. Currently, he is a Full Professor at the Politecnico di Milano, Milano, Italy and Università della Svizzera italiana, Lugano, Switzerland. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), A*STAR (SIN), and UKobe (JP). Dr. Alippi is an IEEE Fellow, Board of Governors member of the International Neural Network Society, Board of Directors member of the European Neural Network Society, Past Vice-President education of the IEEE Computational Intelligence Society, past Associate editor of the IEEE Computational Intelligence Magazine, the IEEE-Transactions on Instrumentation and Measurements, the IEEE-Transactions on Neural Networks. In 2016 he received the Gabor award from the International Neural Networks Society and the IEEE Computational Intelligence Society Outstanding Transactions on Neural Networks and Learning Systems Paper Award; in 2013 the IBM Faculty award; in 2004 the IEEE Instrumentation and Measurement Society Young Engineer Award. Current research activity addresses adaptation and learning in non-stationary environments and Intelligence for embedded and cyber-physical systems. He holds 5 patents, has published one monograph book, 6 edited books and more than 200 papers in international journals and conference proceedings.

Affiliations and expertise

Professor, Politecnico di Milano, Milano, Italy; Università della Svizzera Italiana, Lugano, Switzerland

Yoonsuck Choe

Dr. Yoonsuck Choe Ph.D. received his B.S. degree in computer science from Yonsei University, Seoul, Korea, and his M.S. and Ph.D. degrees in computer sciences from the University of Texas at Austin, Austin, Texas, USA. He is Professor and Director of the Brain Networks Laboratory in the Department of Computer Science and Engineering at Texas A&M University. During 2017 to 2019, he led the machine learning lab and the AI core team at Samsung Research as a corporate vice president. His research interest is broadly in imaging, modeling, and understanding brain function, from the local circuit level up to the whole brain scale, with a focus on the temporal and sensorimotor aspects of brain operation. He has published extensively in the above areas with over 140 publications that include three best paper awards and one best paper award nomination. He served as the program chair for the International Joint Conference on Neural Networks in 2015, and as the general chair in 2017. He is currently on the editorial board of IEEE Transactions on Cognitive and Developmental Systems.

Affiliations and expertise

Professor and Director, Brain Networks Laboratory, Department of Computer Science and Engineering, Texas A&M University, USA

Francesco Carlo Morabito

Dr. Francesco Carlo Morabito Ph.D was born in Italy and educated in Europe. He earned the “Laurea” Degree (Summa cum laude) from the University of Napoli (Italy) and he began his career as a Research Associate at Selenia SpA, Rome, (Radar Department). He joined the University of Reggio Calabria, Italy, as research associate, then becoming Associate Professor and Full Professor of Electrical Engineering. He served as Chair of the Electronic Engineering Course and of the Industrial Engineering Course, as member of the University’s Inner Evaluation Committee, as Dean of the Faculty of Engineering, member of the Bylaws Committee, and serves now as Deputy Rector and Vice-Rector for Internationalization. He also taught at the EPFL, Lausanne, Switzerland (Ph.D. level), University of Naples, University of Messina, and University of Cosenza. He was a selected teacher at the Italian School of Doctorate in Electrical Engineering. Visiting Researcher Max-Planck Institute fuer Plasmaphysiks Munich, Germany. He is author/co-author of 300+ papers on international journals/conferences, 20 book chapters; and editor/co-editor of 10 international books, as well as Guest Editor for two special Issues of Neural Networks and IEEE Sensors. He is a Foreign Member of the Royal Academy of Doctors, Barcelona, Spain; Gold Medal “Henry Coanda”, Rumanian Academy for Researches in Neural Networks and Fuzzy Systems, Iasi, Rumania; President of the Italian Society of Neural Networks (SIREN). Positions held within INNS: Member of the Board of Governors; Secretary; Member of the Board of Governors; Chair of the Nomination Committee; Plenary Chair at IJCNN 2015; Tutorial Chair in many Editions of IJCNN. Senior Member of IEEE and INNS. Italian Representative in AMSE, SIGEF. Delegate for European University Association (EUA). He holds three patents. He founded the University Spin-Off “Neuratek” in 2005. Associate Editor of Neural Networks (Elsevier); Int. J. of Neural Systems; Editorial Board Member for: Renewable Energy (Elsevier); Applied Computational Intelligence and Soft Computing; Recent Patents in Computer Science; Intl. Journal of Computers, Signals and Systems; Fuzzy Economy Review; Micro- and Nano-Sensing Journal, Intl. Journal of Information Acquisition.

Affiliations and expertise

AI_Lab-NeuroLab, Diceam, University Mediterranea of Reggio Calabria, Reggio Calabria, Italy