In the 90s , with the development of distributed computing , distributed object computing ( doc ) has been the main stream of distributed computing 進(jìn)入90年代,隨著分布計算技術(shù)的發(fā)展,分布對象計算已成為分布計算的主流。
The grid technology is primary combination and development of many technologies , such as high perform computing , distributed technology , intemt and so on 它是高性能計算機、分布式技術(shù)、因特網(wǎng)等幾種技術(shù)的有機組合和發(fā)展。
The key of bp neural network is the capacity of parallel computing , distributed saving , self - studying , fault - tolerant and nonlinear function approximating Dp神經(jīng)網(wǎng)絡(luò)不僅具有并行運算、分布式存儲、自學(xué)習(xí)、容錯能力強等特征,還具有無限逼近非線性函數(shù)的能力。
As in nature , the network function is determined largely by connections ( weights ) between elements , so that a particular input leads to a specific target output . the cores of backpropagation neural network are the capacity of parallel computing , distribute saving , self - studying , fault - tolerant and nonlinear function approximating . input vectors and the corresponding target vectors are used to train a network until it can approximate a function , associate input vectors with specific output vectors , or classify input vectors in an appropriate way as defined by you 人工神經(jīng)網(wǎng)絡(luò)是一類模擬人類神經(jīng)系統(tǒng)的結(jié)構(gòu),他揭示數(shù)據(jù)樣本中蘊含的非線性關(guān)系,大量處理單元組成非線性自適應(yīng)動態(tài)系統(tǒng),具有良好的自適應(yīng)性、自組織及很強的學(xué)習(xí)、聯(lián)想、容錯和抗干擾能力,在不同程度和層次上可模仿大腦的信息處理機理,可靈活方便的對多成因的復(fù)雜未知系數(shù)進(jìn)行建模。