...
首页> 外文期刊>Pattern recognition and image analysis: advances in mathematical theory and applications in the USSR >Inductive Method of Choosing a Model with the Least Error and Bias for Solving Interpolation Tasks of Artificial Intelligence
【24h】

Inductive Method of Choosing a Model with the Least Error and Bias for Solving Interpolation Tasks of Artificial Intelligence

机译:求解人工智能插值任务的误差最小偏差模型的归纳法

获取原文
获取原文并翻译 | 示例
           

摘要

The set of objects presented for recognition or dependence detection can be closed, i.e., limited. In this case, in order to choose an optimal model in the given collection of models-candidates, it is reasonable to use the external criterion of the least error. If data are accurate enough, model selection is ambiguous. Then, for additional determination of a model, it is recommended to use a bias criterion for searching. A new cross criterion of the model bias is introduced and applied. It is much easier for calculation than the criterion of the model bias obtained with the help of sample separation into two statistically identical parts.
机译:呈现的用于识别或依赖性检测的对象的集合可以是封闭的,即是有限的。在这种情况下,为了在给定的模型候选集合中选择最佳模型,使用误差最小的外部准则是合理的。如果数据足够准确,则模型选择不明确。然后,为了进一步确定模型,建议使用偏差准则进行搜索。引入并应用了模型偏差的新交叉准则。与通过将样本分为两个统计上相同的部分而获得的模型偏差的标准相比,计算起来要容易得多。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号