conditional neural process

From statwiki
Revision as of 17:30, 18 November 2018 by S366chen (talk | contribs) (Created page with "== Introduction == To train a model effectively, deep neural networks require large datasets. To mitigate this data efficiency problem, learning in two phases is one approach...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Introduction

To train a model effectively, deep neural networks require large datasets. To mitigate this data efficiency problem, learning in two phases is one approach : the first phase learns the statistics of a generic domain without committing to a specific learning task; the second phase learns a function for a specific task, but does so using only a small number of data points by exploiting the domain-wide statistics already learned.

For example, consider a data set ${x_i, y_i}$