术语“转导推理”的详细信息

英译术语:

transductive inference

汉语语境:

支持向量机（SVM）方法是一种有坚实理论基础的新颖的小样本学习方法，它基本上不涉及概率测度及大数定律等，因此不同于现有的统计方法。从本质上看，它避开了从归纳到演绎的传统过程，实现了高效的从训练样本到预报样本的“转导推理”，大大简化了通常的分类和回归等问题。

英语语境:

Support Vector Machine (SVM) is a novel learning method that has solid theoretical basis and requires only small amount of sample. It does not rely on probability measures or Law of Large Numbers, hence it is different from many other statistical methods. In essence, SVM smartly evades the traditional inference process from induction to deduction. Instead, it employs transductive inference from training sample to predicting sample, which greatly simplifies classification and regression problems.