Evolving spatio-temporal data machines based on the neucube neuromorphic framework: design methodology and selected applications

Kasabov, Nikola and Scott, Nathan Matthew and Tu, Enmei and Marks, Stefan and Sengupta, Neelava and Capecci, Elisa and Othman, Muhaini and Doborjeh, Maryam and Murli, Norhanifah and Hartono, Reggio and Espinosa-Ramos, Josafath Israel and Lei, Zhou and Alvi, Fahad Bashir and Wang, Grace and Taylor, Denise and Feigin, Valery and Gulyaev, Sergei and Mahmoud, Mahmoud and Hou, Zeng-Guang and Yang, Jie (2016) Evolving spatio-temporal data machines based on the neucube neuromorphic framework: design methodology and selected applications. Neural Networks, 78 . pp. 1-14. ISSN 08936080

[img]
Preview
PDF
21Mb

Abstract

The paper describes a new type of evolving connectionist systems (ECOS) called evolving spatio-temporal data machines based on neuromorphic, brain-like information processing principles (eSTDM). These are multi-modular computer sys- tems designed to deal with large and fast spatio/spectro temporal data using spiking neural networks (SNN) as major processing modules. ECOS and eSTDM in particular can learn incrementally from data streams, can include `on the y' new input variables, new output class labels or regression outputs, can continuously adapt their structure and func- tionality, can be visualised and interpreted for new knowledge discovery and for a better understanding of the data and the processes that generated it. eSTDM can be used for early event prediction due to the ability of the SNN to spike early, before whole input vectors (they were trained on) are presented. A framework for building eSTDM called NeuCube along with a design methodology for building eSTDM using it is presented. The implementation of this frame- work in MATLAB and in PyNN is presented, the latter facilitating the use of neuromorphic hardware platforms to run the eSTDM. Selected examples are given of eSTDM for pattern recognition and early event prediction on EEG data, fMRI data, multisensory seismic data, ecological data, climate data, audio-visual data. Future directions are discussed, including extension of the NeuCube framework for building neurogenetic eSTDM and also new applications of eSTDM.

Item Type:Article
Uncontrolled Keywords:Spatio/spectro temporal data; evolving connectionist systems; evolving spiking neural networks; computational neurogenetic systems; evolving spatio-temporal data machines; NeuCube;
Subjects:T Technology > T Technology (General)
Divisions:Faculty of Computer Science and Information Technology > Department of Software Engineering
ID Code:8388
Deposited By:Mr. Mohammad Shaifulrip Ithnin
Deposited On:25 Apr 2017 15:52
Last Modified:25 Apr 2017 15:52

Repository Staff Only: item control page