Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications
Article
Article Title | Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications |
---|---|
ERA Journal ID | 18090 |
Article Category | Article |
Authors | Kasabov, Nikola (Author), Scott, Nathan Matthew (Author), Tu, Enmei (Author), Marks, Stefan (Author), Sengupta, Neelava (Author), Capecci, Elisa (Author), Othman, Muhaini (Author), Doborjeh, Maryam Gholami (Author), Murli, Norhanifah (Author), Hartono, Reggio (Author), Espinosa-Ramos, Josafath Israel (Author), Zhou, Lei (Author), Alvi, Fahad Bashir (Author), Wang, Grace (Author), Taylor, Denise (Author), Feigin, Valery (Author), Gulyaev, Sergei (Author), Mahmoud, Mahmoud (Author), Hou, Zeng-Guang (Author) and Yang, Jie (Author) |
Journal Title | Neural Networks |
Journal Citation | 78, pp. 1-14 |
Number of Pages | 14 |
Year | 2016 |
Place of Publication | United Kingdom |
ISSN | 0893-6080 |
1879-2782 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.neunet.2015.09.011 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0893608015001860 |
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 systems 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 fly' new input variables, new output class labels or regression outputs, can continuously adapt their structure and functionality, 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 this is presented. The implementation of this framework in MATLAB, Java, and PyNN (Python) is presented. The latter facilitates 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. |
Keywords | Computational neurogenetic systems; Evolving connectionist systems; Evolving spatio-temporal data machines; Evolving spiking neural networks; NeuCube; Spatio/spectro temporal data |
ANZSRC Field of Research 2020 | 520499. Cognitive and computational psychology not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Auckland University of Technology, New Zealand |
Chinese Academy of Sciences, China | |
Shanghai Jiao Tong University, China | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q750y/evolving-spatio-temporal-data-machines-based-on-the-neucube-neuromorphic-framework-design-methodology-and-selected-applications
96
total views4
total downloads1
views this month0
downloads this month