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

Kasabov N 1 , Scott NM 2 , Tu E 3 , Marks S 4 , Sengupta N 3 , Capecci E 3 Show all authors , Othman M 5 , Doborjeh MG 3 , Murli N 3 , Hartono R 3 , Espinosa-Ramos JI 6 , Zhou L 7 , Alvi FB 3 , Wang G 8 , Taylor D 9 , Feigin V 10 , Gulyaev S 11 , Mahmoud M 11 , Hou ZG 12 , Yang J 13

Affiliations 

  • 1 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand. Electronic address: [email protected]
  • 2 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand. Electronic address: [email protected]
  • 3 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand
  • 4 CoLab, Auckland University of Techology, Auckland, New Zealand
  • 5 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand; Universiti Tun Hussein Onn Malaysia, Johor, Malaysia
  • 6 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand; Centro de Investigación en Computación, Instituto Politécnico Nacional, Mexico
  • 7 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand; Shanghai Jiao Tong University, Shanghai, China
  • 8 Gambling & Addictions Research Centre, Auckland University of Technology, Auckland, New Zealand
  • 9 Health & Rehabilitation Research Centre, Auckland University of Technology, Auckland, New Zealand
  • 10 National Institute for Stroke and Applied Neurosciences, Auckland University of Technology, Auckland, New Zealand
  • 11 Institute for Radio Astronomy & Space Research, Auckland University of Technology, Auckland, New Zealand
  • 12 State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
  • 13 Shanghai Jiao Tong University, Shanghai, China
Neural Netw, 2016 Jun;78:1-14.
PMID: 26576468 DOI: 10.1016/j.neunet.2015.09.011

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.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

MeSH terms
Similar publications