Estimation of Network Parameters in Semiparametric Stochastic Perceptron
Estimation of Network Parameters in Semiparametric Stochastic Perceptron
复制标题
半参数随机感知器中网络参数的估计
DOI：
10.1162/neco.1994.6.6.1244
复制
发表时间：
1994
影响因子：
2.9
通讯作者：
S. Amari
中科院分区：
文献类型：
--
作者：
M. Kawanabe;S. Amari
据报道（Kabashima和Shinomoto 1992），当概率模型是不适定或半参数时，二元决策边界的估计量显示出渐近奇怪的行为。本文用估计函数方法对随机感知器中的这一现象进行了严格的分析。随机感知器由一个神经元组成，该神经元根据输入的加权和而兴奋，但其概率分布形式在这里是未知的。结果表明，不存在阈值h的n-相容估计，也就是说，不存在随着观测数n的增加而以1/ n阶收敛于h的估计.因此，估计的准确性是在这种半参数的情况下，一个未指定的概率函数比在普通情况下差得多。另一方面，它表明，有一个n-一致的估计的突触权重向量。这些结果阐明了半参数统计模型中学习曲线的奇怪行为。
It was reported (Kabashima and Shinomoto 1992) that estimators of a binary decision boundary show asymptotically strange behaviors when the probability model is ill-posed or semiparametric. We give a rigorous analysis of this phenomenon in a stochastic perceptron by using the estimating function method. A stochastic perceptron consists of a neuron that is excited depending on the weighted sum of inputs but its probability distribution form is unknown here. It is shown that there exists no n-consistent estimator of the threshold value h, that is, no estimator h that converges to h in the order of 1/ n as the number n of observations increases. Therefore, the accuracy of estimation is much worse in this semiparametric case with an unspecified probability function than in the ordinary case. On the other hand, it is shown that there is a n-consistent estimator of the synaptic weight vector. These results elucidate strange behaviors of learning curves in a semiparametric statistical model.
S.Amari：神经网络。
DOI：
--
发表时间：
--
期刊：
影响因子：
--
作者：
通讯作者：
--