conditional neural process: Difference between revisions
Jump to navigation
Jump to search
| Line 4: | Line 4: | ||
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. | 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 <math display="inline"> {x_i, y_i} </math> for <math display="inline">i = 0 | For example, consider a data set <math display="inline"> \{x_i, y_i\} </math> for <math display="inline">i = 0,..., n-1</math> | ||
Revision as of 16:34, 18 November 2018
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 [math]\displaystyle{ \{x_i, y_i\} }[/math] for [math]\displaystyle{ i = 0,..., n-1 }[/math]