solidot新版网站常见问题,请点击这里查看。
消息
本文已被查看3046次
How Deep Are Deep Gaussian Processes?. (arXiv:1711.11280v1 [math.ST])
来源于:arXiv
Recent research has shown the potential utility of probability distributions
designed through hierarchical constructions which are conditionally Gaussian.
This body of work is placed in a common framework and, through recursion,
several classes of deep Gaussian processes are defined. The resulting samples
have a Markovian structure with respect to the depth parameter and the
effective depth of the process is interpreted in terms of the ergodicity, or
non-ergodicity, of the resulting Markov chain. 查看全文>>