learning vector quantization

基本解釋

Neurons can not be taken to full advantage and the information between feature vectors and neurons is wasted among supervised learning vector quantization (LVQ)neural networks.
針對(duì)監(jiān)督LVQ神經(jīng)網(wǎng)絡(luò)存在神經(jīng)元未被充分利用以及輸入樣本和競(jìng)爭(zhēng)單元之間的信息被浪費(fèi)等問題。
The principle of fuzzy vector quantization (FVQ) for image coding is discussed in this paper, and an exponential fuzzy learning vector quantization algorithm (EFLVQ) is proposed.
本文分析了模糊矢量量化（FVQ）圖像編碼的原理，提出了一種指數(shù)型模糊學(xué)習(xí)矢量量化算法（EFLVQ）。
In this paper, four neural networks, i. e. multi layer perception, radial basis function, learning vector quantization and self organizing feature mapping, are used to segment the flame image.
本文研究了多層感知器、徑向基函數(shù)網(wǎng)絡(luò)、學(xué)習(xí)向量量化網(wǎng)絡(luò)和自組織特征映射網(wǎng)絡(luò)等四種神經(jīng)網(wǎng)絡(luò)在回轉(zhuǎn)窯火焰圖像分割中的應(yīng)用。

improved learning vector quantization 改進(jìn)的學(xué)習(xí)向量量化
learning vector quantization algorithm 學(xué)習(xí)向量量化算法
Learning Vector Quantization algorithms 學(xué)習(xí)矢量量化算法
Learning Vector Quantization Network 學(xué)習(xí)向量量化網(wǎng)路;學(xué)習(xí)矢量量化網(wǎng)絡(luò);量量化網(wǎng)絡(luò)
competitive learning vector quantization 競(jìng)爭(zhēng)學(xué)習(xí)矢量量化