Probabilistic visualisation of high-dimensional binary data
M Tipping - Advances in neural information processing …, 1998 - proceedings.neurips.cc
Advances in neural information processing systems, 1998•proceedings.neurips.cc
We present a probabilistic latent-variable framework for data visu (cid: 173) alisation, a key
feature of which is its applicability to binary and categorical data types for which few
established methods exist. A variational approximation to the likelihood is exploited to derive
a fast algorithm for determining the model parameters. Illustrations of application to real and
synthetic binary data sets are given.
feature of which is its applicability to binary and categorical data types for which few
established methods exist. A variational approximation to the likelihood is exploited to derive
a fast algorithm for determining the model parameters. Illustrations of application to real and
synthetic binary data sets are given.
Abstract
We present a probabilistic latent-variable framework for data visu (cid: 173) alisation, a key feature of which is its applicability to binary and categorical data types for which few established methods exist. A variational approximation to the likelihood is exploited to derive a fast algorithm for determining the model parameters. Illustrations of application to real and synthetic binary data sets are given.
proceedings.neurips.cc
以上显示的是最相近的搜索结果。 查看全部搜索结果