Time-space, spiking neural networks and brain-inspired artificial intelligence
by Nikola Kasabov, 2018
738 pages
Springer Series on Bio- and Neurosystems:
Springer Nature,Switzerland AG
Part of Springer Nature
OVERVIEW
Spiking neural networks (SNN) are biologically inspired computational models that represent and process information internally as trains of spikes. This monograph book presents the classical theory and applications of SNN, including original author’s contribution to the area.
The book introduces for the first time not only deep learning and deep knowledge representation in the human brain and in brain-inspired SNN, but takes that further to develop new types of AI systems, called in the book brain-inspired AI (BI-AI).
BI-AI systems are illustrated on: cognitive brain data, including EEG, fMRI and DTI; audio-visual data; brain-computer interfaces; personalized modelling in bio-neuroinformatics; multisensory streaming data modelling in finance, environment and ecology; data compression; neuromorphic hardware implementation. Future directions, such as the integration of multiple modalities, such as quantum-, molecular- and brain information processing, is presented in the last chapter.
The book is a research book for postgraduate students, researchers and practitioners across wider areas, including computer and information sciences, engineering, applied mathematics, bio- and neurosciences.
Forward by Prof. Steve Furber, University of Manchester.
To order
Click to order the book from Springer's website
Downloads: 33,000+ (09 May 2021)
Reviews
Prof. Juan H. Sossa Azuela, Mexico: One of the most interesting books in the area
"Since I obtained this book and begin to read it, I realize that it could be used as a reference by all those interested in beginning and going deep into the field of spiking neural networks. It really inspired me to continue with this fascinating study" (Amazon.com).
Prof. CS Calude (U of Auckland, NZ): Hot topics in Artificial Intelligent Systems
"This monograph presents the state of the art in evolving connectionist systems. spiking neural networks and new developments in brain-inspired artificial intelligent systems. The book is well written and rich in information, implementations, and applications, developed over many years by the author and his team. It also includes a detailed list of references. I benefited most from the chapters on personalized modelling and quantum-inspired evolutionary optimization techniques. This excellent research book can be used by postgraduate students, academics, and practitioners in computer science, engineering, neuro-, and bio-informatics" (Amazon.com.au)
Dr M Doborjeh: A very comprehensive research book
"A very comprehensive research book that includes novel methods and technology for modelling and analysing big, complex spatiotemporal data across wider areas. I am the lecturer of Neuroinformatics, which is a postgraduate course at Auckland University and Technology and recommended this book to my students as a rich source of state-of-the-art research to improve their research informed assignment (www.kobo.com)
Dr D.Filev, Senior Scientists, Ford, USA
"It is a true Encyclopedia of Computational Intelligence. I really liked your vision for BI-AI - a monumental contribution to computer science."
Prof. Steve Furber, University of Manchester:
“ … This book is not just a record of past work, but also a guide book for an exciting future” (from the Forward to the book)
Prof. Plamen Angelov, Lancaster University, UK
“…Your book is very insightful and forward looking!”
A/Prof. Basabdatta Sen Bhattacharya (PI of the Brain Inspired Neural Networks (BINN) Labs)
https://www.binnlabs-goa.in/; Email: basabdattab@goa.bits-pilani.ac.in
“I am teaching a reading course “Brain inspired deep learning and applications” using this book as a main text. The class is full. I feel privileged to have access to your guidance, Nik, on conducting the course. It was exciting for me to see India on the map of the NeuCube community! Thank you!”
Iman AbouHassan, Director at the Beirut Central Bank: Indispensable AI novel
(https://www.goodreads.com/review/show/4067839156).
"A great book, a good reference, and an enjoyable read on the evolution of AI methods. It travels us back in time, passing the torch of knowledge, faithfully conveying it from Aristotle to this moment onwards. The book explores the importance of ‘Time’ and highlights the future role of evolving spiking neural networks to achieve ‘Oneness’ in data modelling using brain-inspired computation. The challenges today are in the field of ethics and fair AI. Human intelligence must lead superiority in order to develop and control new artificial intelligence technologies.
This book is very informative and an inspiration to me. It is highly recommended not only to academics but also to engineers, economists, and researchers seeking an in-depth, up-to-date overview of the paradigm shift of technologies and innovation systems. Just as it found its success in medicine, it should be rooted in the area of economics and finance. I am very happy to embark on my PhD journey inspired by this book.
Thank you prof. Kasabov for the outstanding and comprehensive work, and I hope you will be further inspired to carry on your mission. Our life is touched by AI; this book is an indispensable AI novel that should be on every shelf and e-library. It sparks in us so that we can, in our own way, spread the light and illuminate the world. Light is everything plus power ... even to me."
errata
Page 49:
Fig.2.10….lateral connections (after [33]).
Page 474:
Acknowledgements: …, L.Paulun, …
Page 475:
[26] A. Wendt, G. Saraceno, L. Paulun, N. Kasabov, Audio-visual data processing and concept
formation (internal report), https://kedri.aut.ac.nz/R-and-D-Systems/audio-visual-data-processing-and-concept-formation
Page 541:
[34] E.Capecci, J. L. Lobo, I.Lana, J. I. Espinosa Ramos, N.Kasabov, Modelling gene interaction networks from time-series gene expression data using evolving spiking neural networks. Evolving Systems 11, 599–613 (2020); https://doi.org/10.1007/s12530-019-09269-6;
Page 656:
[31] R. Khansama, V. Ravi, N. Sengupta, A.R. Gollahalli, N. Kasabov, I. Bilbao-Quintana, Stock market movement prediction using evolving spiking neural networks, in: Vadlamani Ravi, Aswani Kumar Cherukuri (Eds) 2nd volume of the series on Handbook on Big Data Analytics, published by IET Publishers, UK, 2021.
Page 603:
Fig.18.7………………(Fig.18.6 and 18.7 …).
supplementary MATERIAL
Preface xiii
First paragraph, last sentence: I acknowledge also A/Prof Hideaki Kawano.
Last paragraph, last sentence: Copyright permissions have been obtained for the inclusion of excerpts from previous publications of the author, if such were required.
Page 141:
Fig. 4.11…………………[31], [38] and also: https://www.izhikevich.org
Page 198:
Acknowledgement: ….Dr J.Lobo drew Fig.5.1b and later led the following publication: J. L. Lobo, I.Laña, J. Del Ser, M.N.Bilbao, N.Kasabov Evolving Spiking Neural Networks for online learning over drifting data streams, Neural Networks, 108, 1-19 (2018).
Page 229:
Acknowledgement: ….Dr Josephat Israel Espinosa-Ramos drew Fig.6.19 and later developed the NeuCube open source simulator in Java, now available from: https://github.com/Auckland-University-of-Technology/NeuCube-java.
Page 330:
Acknowledgement:….A/P Hideaki Kawano from KIT Japan contributed to the research in section 8.4 (see also [43]).
Page 499:
Acknowledgement:…Akshay Gollahalli created Fig.14.16 [50]. Later he developed a NeuCube software cloud version: https://neucube.io.
Page 587:
Acknowledgements: …………………….More specifically a PhD student Vinita Kumar Jansari contributed to the sub-section 17.3.3, also partially published in a newly added reference [58] and a Masters student Mary Ann Ribeiro for a contribution to sub-section 17.3.4, partially published in [56]. Vinita created Fig.17.9 and Marry Ann – Figs.7.10 and 7.11.
Page 588:
[58] Jansari, V., Kasabov, N., & Pears, R. (2017). PM-Py: An Open Source Personalised Predictive Modelling System: A case-study on Personalised Modelling Architecture, 2017 Health Informatics New Zealand Conference, Rotorua, New Zealand.
Page 653:
Acknowledgements: …… Details of the experiments in section 19.3 are presented in [61],[63] and [64]. Details of experiments in section 19.4 are presented in [1] and [61]
Page 658 new references:
[63] E. Tu, N. Kasabov, M.Othman, Y. Li, S.Worner, J.Yang and Z. Jia, NeuCube(ST) for Spatio-Temporal Data Predictive Modelling with a Case Study on Ecological Data, Proc. WCCI 2014, Beijing, 7-13 July 2014, IEEE Press.
[64] R. Hartono, R. Pears, N. Kasabov and S. Worner, Extracting Temporal Knowledge from Time Series: A Case Study in Ecological Data, Proc. WCCI 2014, Beijing, 7-13 July 2014, IEEE Press.