固定输入分布下学习二元输出神经网络样本复杂性的一个注记
A note on sample complexity of learning binary output neural networks under fixed input distributions
摘要:
我们证明了Sontag(1992)构造的S形神经网络的学习样本复杂度在固定的纯原子分布下达到给定的误分类错误所需的复杂度可以任意快速地增长:对于任何指定的增长率,都存在一个以该增长率为样本复杂度的输入分布,并且该边界是渐近紧的。率可以是超指数,非递归函数等,我们进一步观察到,桑塔格的人工神经网络是不是Glivenko-Cantelli下的任何输入分布具有非原子部分。
英文摘要:
We show that the learning sample complexity of a sigmoidal neural network constructed by Sontag (1992) required to achieve a given misclassification error under a fixed purely atomic distribution can grow arbitrarily fast: for any prescribed rate of growth there is an input distribution having this rate as the sample complexity, and the bound is asymptotically tight. The rate can be superexponential, a non-recursive function, etc. We further observe that Sontag's ANN is not Glivenko-Cantelli under any input distribution having a non-atomic part.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。