Difference between revisions of "conditional neural process"

From statwiki
Jump to: navigation, search
(Introduction)
(Introduction)
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,..., n-1</math> with evaluations <math display="inline">y_i = f(x_i) </math> for some unknown function <math display="inline">f</math>. Assume <math display="inline">g</math> is an approximating function of f. The aim is yo minimize the loss between <math display="inline">f</math> and  <math display="inline">g</math> on the entire space  <math display="inline">X</math>
+
For example, consider a data set <math display="inline"> \{x_i, y_i\} </math>  with evaluations <math display="inline">y_i = f(x_i) </math> for some unknown function <math display="inline">f</math>. Assume <math display="inline">g</math> is an approximating function of f. The aim is yo minimize the loss between <math display="inline">f</math> and  <math display="inline">g</math> on the entire space  <math display="inline">X</math>. In practice, the routine is evaluated on a finite set of observations.
 +
 
 +
In this work, they proposed a family of models that represent solutions to the supervised problem, and ab end-to-end training approach to learning them, that combine neural networks with features reminiscent if Gaussian Process. They call this family of models Conditional Neural Processes.

Revision as of 17:13, 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] \{x_i, y_i\} [/math] with evaluations [math]y_i = f(x_i) [/math] for some unknown function [math]f[/math]. Assume [math]g[/math] is an approximating function of f. The aim is yo minimize the loss between [math]f[/math] and [math]g[/math] on the entire space [math]X[/math]. In practice, the routine is evaluated on a finite set of observations.

In this work, they proposed a family of models that represent solutions to the supervised problem, and ab end-to-end training approach to learning them, that combine neural networks with features reminiscent if Gaussian Process. They call this family of models Conditional Neural Processes.