表紙画像

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...

詳細記述

保存先:
書誌詳細
主要な著者: 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
フォーマット: 論文
言語:English
出版事項: Springer International Publishing 2018
主題:
NA Architecture
T Technology (General)
オンライン･アクセス: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
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
その他の書誌記述
要約: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.

類似資料