在”证明“股票基于价格与成交量的技术分析是不可行的”  一贴中本人提供了证明的思路与文献今天，经长期思考，为它提供一更具实际价值的定理。。鉴于本人都是用英文学习这方面的内容，因此用英文来表述它更正确，

”For any infinite domain set, X,  the class of all binary valued functions over X is not a countable union of classes of finite VC-dimension .  It follows that whenever the domain is not finite, there exists no nonuniform learner with respect to the class of all binary classifiers (although for each such classifier there exists a trivial algorithm that learns it – ERM with respect to the
hypothesis class that contains only this classifier)."


这有几个重要的概念：“nonuniform learner"  其实质是‘可学习性’概念中最弱的一个。
'VC-dimension'   学习假设的复杂性的测定
”ERM“  样本误差最小化

很对不起，不再证明它！！