Natural Intelligence Neuromorphic Engineering (NINE) provides readers with the most recent breakthrough advances in Deep Learning, computational intelligence and Artificial Neural Networks (ANN), providing detailed research and explanations of the physics and physiology principles used in developing Natural Intelligence for unsupervised learning of Blind Sources Separation (BSS). Author Harold Szu, a world-renowned pioneer in natural intelligence development, will assemble a team of experts to cover the latest trends in deep learning, including improving the robust internal knowledge representation, big database data mining, and real time optical flow. This collaborative work will offer researchers and graduate students alike with the most up-to-date information on the theories and key applications in natural intelligence and deep learning towards real-time, error-free, and automatic target recognition.
- The only book that covers natural intelligence uses in today’s fast-advancing computational intelligence applications
- Features MATLAB codes in each chapter, which will be made available as free downloads for readers
- Provides a short and concise explanation of the physics and physiological principles necessary for developing natural intelligence through unsupervised learning and blind sources separation (BSS)
Research Engineers working on artificial neural networks, Biomedical Engineers, Biomechanical Engineers, and Electrical Engineers
Chapter 1: Rule-Based Artificial Intelligence versus Artificial Neural Network Learning (ANN) Using Hinton and Jordan Deep Learning
Chapter 2: Theorem of Natural Intelligence (NI): Necessary and Sufficient Conditions for D.O. Hebb Unsupervised Learning Rule
o Physics of Blind Sources Separations versus Mathematics ICA of Joint-density factorization
o Further improving deep learning brittleness the Internal Knowledge Representation (IKR) by solving the direct sensor measurement and inverse sources inference problems
Chapter 3: Improving Deep Learning through Associative Memory Expert Systems, Multiple layer Deep Learning, Compressive Sensing, Capture Novelty Detection
Chapter 4: Traditional ANN, Neural Dynamics, and the Lyapunov Convergence Theorem
o Hopfield & Tank Model
o Adaptive Resonance Theory;
o Recurrent Networks
Chapter 5: Stochastic Divide & Conquer by Fast-Simulated Annealing Searching of the Global Minimum
Chapter 6: ANN Smart Sensors & Human Visual Systems Automation to the Industry
Chapter 7: Biological Chaotic Neural Networks Modeling & VLSI Implementations
Chapter 8: Fuzzy Logic with Possibility versus Probability Membership Functions
Chapter 9: ANN Pattern Recognition & Aided Target Recognition
Chapter 10: Ear-like Adaptive Wavelet Processing with Szu’s Super-Mother Wavelet Theorem
Chapter 11: ANN Financial Analyses
Chapter 12: How Smartphones with Big Databases Analysis ANN Can Help Public Health
o Early Screening of Breast Cancers and Skin Cancers
Chapter 13: ANN Smartphone with MEMS Smart Nodes can Nowcast Earthquakes
o Brain Computer EEG Interfaces and Heartbeat QRST-Wave Interfaces
- No. of pages:
- © Academic Press 2019
- 1st January 2019
- Academic Press
- Paperback ISBN:
Dr. Szu has been a champion of components of human sciences (http://www.ica-wavelet.org) and brain-style computing for 2 decades;
he received the INNS D. Gabor Award in 1997 and the Eduardo R. Caianiello Award in 1999 from the Italy Academy.
Recently, he contributed to the unsupervised learning theory of the thermodynamic free energy of sensory pair for fusion. Besides 440 publications,
(cf. https://www.researchgate.net/profile/Harold_Szu2) over dozen US patents, numerous books & journals, conference proceedings.
Dr. Szu taught students “how to be creative in interdisciplinary sciences” according to the Reinsurance Individual and Team Creativity Methodology,
and guided over a dozen PhD students. (http://www.genealogy.math.ndsu.nodak.edu/id.php?id=44103).
He received a Ph.D. in Theoretical Physics from G.E. Uhlenbeck of the Rockefeller Univ., New York, NY.
He began at NRL, NSWC, ONR, and now a senior scientist at Army Night Vision Electronic Sensor Director, Ft. Belvoir, VA.
Since CUA has campus on Ft. Belvoir, Prof. Szu left GWU and is appointed as Professor of CUA (http://biomedical.cua.edu/faculty-staff/Szu.cfm)
• Fellow of AIMBE 2004 for breast cancer passive spectrogram diagnoses.
• Fellow of IEEE (1997) for bi-sensor fusion;
• Foreign Academician, RAS 1999, for unsupervised learning.
• Fellow of OSA (1996) for adaptive wavelet
• Fellow of SPIE since 1995 for neural nets.
• Fellow of INNS (2010) for a founder and former president
Senior Scientist, U.S. Army Night Vision and Electronic Sensors Directorate and Biomedical Engineering Research Professor, Catholic University of America