摘要:
根据成长函数的定义,猜测 ——>break point K restricts maximum possible mh(N) a lot for N>k bounding functionB(N, k): maximum possible mH(N) when break point = k 下面是 阅读全文
摘要:
for batch&supervised binary classfication,g≈f <=> Eout(g)≥0 achieved through Eout(g)≈Ein(g) and Ein(g)≈0 其中Ein是某一个备选函数h在数据D上犯错误的比例,在整个数据集上犯错误的比例为Eout 阅读全文