In the paper a parallel analogue implementation of the 'winner-take-all' function is proposed. It can be utilised in the hardware realisation of neurocomputer systems based on competitive learning, which find application in areas such as pattern classification, vector quantisation and image recognition. Analytic results are derived by means of the piecewise-linear method in the case of two variables and SPICE simulation results are presented in the general case. It is shown that the circuit exhibits some ad hoc properties that make it well suited for this kind of application.
机构:
Hong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R ChinaHong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R China
Li, Shuai
Zhou, MengChu
论文数: 0引用数: 0
h-index: 0
机构:
Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China
New Jersey Inst Technol, Helen & John C Hartmann Dept Elect & Comp Engn, Newark, NJ 07102 USAHong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R China
Zhou, MengChu
Luo, Xin
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R ChinaHong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R China
Luo, Xin
You, Zhu-Hong
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Urumqi 830011, Peoples R ChinaHong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R China