orthogonal function basis

基本解釋

In the process of application of Improved BP algorithm in PNN, the input functions and the network weight functions are represented as expansion of a same orthogonal function basis.
在改進(jìn)BP算法與網(wǎng)絡(luò)訓(xùn)練的結(jié)合過(guò)程中，權(quán)函數(shù)及輸入函數(shù)皆被用同一正交基函數(shù)展開(kāi)。
In consideration of the complexity of the aggregation operation of time in process neural networks, a new learning algorithm based on function orthogonal basis expansion is proposed.
該文在考慮過(guò)程神經(jīng)網(wǎng)絡(luò)對(duì)時(shí)間聚合運(yùn)算的復(fù)雜性的基礎(chǔ)上，提出了一種基于函數(shù)正交基展開(kāi)的學(xué)習(xí)算法。
And the complex variable moving least-square approximation based on the orthogonal basis function is discussed in detail.
提出了復(fù)變量移動(dòng)最小二乘法，并詳細(xì)討論了基于正交基函數(shù)的復(fù)變量移動(dòng)最小二乘法。