Moreover , this method is robust to the variety of snr and avoids overfitting and local minimum in neural nelwork . the percenlage of correcl idenlificalion for signals is salisfied wilh the fewer training data 該方法在信噪比變化范圍較大的情況下,采用較少的訓(xùn)練數(shù)據(jù)就可以達到令人滿意的識別正確率。
In translation searching process , many ebmt systems can only rely on a heuristic guidance which is given by human . therefore that process will not be objective and always lean much on the intuition of system developer and may be overfitting to a special domain 但是,由于在ebmt系統(tǒng)進行譯文搜索的過程中往往只能依靠人為設(shè)定的啟發(fā)式函數(shù)進行指導(dǎo),對人為因素的依賴較大,很容易造成對某個限定領(lǐng)域特點的過度擬合。