Cover Image

From von Neumann architecture and Atanasoff’s ABC to Neuromorphic Computation and Kasabov’s NeuCube. Part II: Applications

Spatio/Spector-Temporal Data (SSTD) analyzing is a challenging task, as temporal features may manifest complex interactions that may also change over time. Making use of suitable models that can capture the “hidden” interactions and interrelationship among multivariate data, is vital in SSTD investi...

Full description

Saved in:
Bibliographic Details
Main Authors: Doborjeh, Maryam, Doborjeh, Zohreh, Gollahalli, Akshay Raj, Kumarasinghe, Kaushalya, Breen, Vivienne, Sengupta, Neelava, Ramos, Josafath Israel Espinosa, Hartono, Reggio, Capecci, Elisa, Kawano, Hideaki, Othman, Muhaini, Lei, Zhou, Jie, Yang, Bose, Pritam, Chenjie, Ge
Format: Article
Language:English
Published: Springer International Publishing 2018
Subjects:
NA Architecture
T Technology (General)
Online Access:http://eprints.uthm.edu.my/5343/1/AJ%202018%20%28498%29.pdf
http://eprints.uthm.edu.my/5343/
http://dx.doi.org/10.1007/978-3-319-78437-3_2
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Spatio/Spector-Temporal Data (SSTD) analyzing is a challenging task, as temporal features may manifest complex interactions that may also change over time. Making use of suitable models that can capture the “hidden” interactions and interrelationship among multivariate data, is vital in SSTD investigation. This chapter describes a number of prominent applications built using the Kasabov’s NeuCube-based Spiking Neural Network (SNN) architecture for mapping, learning, visualization, classification/regression and better understanding and interpretation of SSTD.

Similar Items