SCALING LAWS IN LEARNING OF CLASSIFICATION TASKS

SCALING LAWS IN LEARNING OF CLASSIFICATION TASKS
复制标题

DOI:
10.1103/physrevlett.70.3167
复制
发表时间:
1993-05-17
影响因子:
8.6
通讯作者:
SOMPOLINSKY, H
SOMPOLINSKY, H
中科院分区:
物理与天体物理1区
文献类型:
--
作者:
BARKAI, N;SEUNG, HS;SOMPOLINSKY, H

文献摘要

被引文献

相似文献

研究了输入分布结构对学习模式分类任务复杂性的影响。使用统计力学,我们研究了赢家通吃机器在学习分类点时的性能,这些点是由R(N)中的K个高斯分布(“聚类”)的混合物产生的,聚类间距离为u(相对于聚类宽度)。在分离极限u >> 1中,学习所需的样本数量为NKu(-p),其中零温吉布斯学习的指数p为2,赫布规则的指数p为4。
The effect of the structure of the input distribution on the complexity of learning a pattern classification task is investigated. Using statistical mechanics, we study the performance of a winner-take-all machine at learning to classify points generated by a mixture of K Gaussian distributions (''clusters'') in R(N) with intercluster distance u (relative to the cluster width). In the separation limit u >> 1, the number of examples required for learning scales as NKu(-p), where the exponent p is 2 for zero-temperature Gibbs learning and 4 for the Hebb rule.