The entropic prior for distributions with positive and negative values
The entropic prior for distributions with positive and negative values
复制标题
具有正值和负值的分布的熵先验
DOI：
10.1046/j.1365-8711.1998.01707.x
复制
发表时间：
1998
影响因子：
4.8
通讯作者：
A. Lasenby
中科院分区：
文献类型：
--
作者：
M. Hobson;A. Lasenby
最大熵方法已被广泛用于天文学领域的图像重建，但在其传统形式中，它仅限于严格正分布的重建。我们提出了一个扩展的标准方法，包括分布，可以采取正值和负值。因此，该方法可以应用于更广泛的天文重建问题。特别是，我们推导出的形式的熵的正/负分布，并使用直接计数参数找到的形式的熵先验。我们还推导出空间上的正/负分布的措施，这使得概率积分的定义，因此适当的量化的错误。
The maximum entropy method has been used to reconstruct images in a wide range of astronomical fields, but in its traditional form it is restricted to the reconstruction of strictly positive distributions. We present an extension of the standard method to include distributions that can take both positive and negative values. The method may therefore be applied to a much wider range of astronomical reconstruction problems. In particular, we derive the form of the entropy for positive/negative distributions and use direct counting arguments to find the form of the entropic prior. We also derive the measure on the space of positive/negative distributions, which allows the definition of probability integrals and hence the proper quantification of errors.