• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual Conference on Neural Information Processing Systems(NIPS); 20031208-13; British Columbia(CA) >Ambiguous model learning made unambiguous with 1/f priors
【24h】

Ambiguous model learning made unambiguous with 1/f priors

机译：模棱两可的模型学习与1 / f先验模棱两可

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

What happens to the optimal interpretation of noisy data when there exists more than one equally plausible interpretation of the data? In a Bayesian model-learning framework the answer depends on the prior expectations of the dynamics of the model parameter that is to be inferred from the data. Local time constraints on the priors are insufficient to pick one interpretation over another. On the other hand, nonlocal time constraints, induced by a 1/f noise spectrum of the priors, is shown to permit learning of a specific model parameter even when there are infinitely many equally plausible interpretations of the data. This transition is inferred by a remarkable mapping of the model estimation problem to a dissipative physical system, allowing the use of powerful statistical mechanical methods to uncover the transition from indeterminate to determinate model learning.
机译：如果存在对数据的多个同等合理的解释，那么对噪声数据的最佳解释会发生什么？在贝叶斯模型学习框架中，答案取决于要从数据推断出的模型参数动态的先前期望。先验的当地时间限制不足以做出一种解释。另一方面，由先验的1 / f噪声频谱引起的非本地时间约束被显示为即使对数据的无限多个同样合理的解释也可以学习特定的模型参数。模型转换问题到耗散物理系统的显着映射可以推断出这种过渡，从而允许使用功能强大的统计力学方法来揭示从不确定模型学习到确定模型学习的过渡。

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