Difference between revisions of "the Wake-Sleep Algorithm for Unsupervised Neural Networks"

From statwiki
Jump to: navigation, search
(Created page with "=Introduction= In considering general learning procedures, supervised methods for neural networks are limited in that they can only be executed in specifically-structured enviro...")
 
Line 2: Line 2:
  
 
In considering general learning procedures, supervised methods for neural networks are limited in that they can only be executed in specifically-structured environments. For these systems to learn, the environment must be equipped with an external "teacher" providing the network with explicit feedback on its predictive performance. From there, the system needs a means for circulating this error information across the entire network, so that the weights can be adjusted accordingly. To apply neural networks in contexts not satisfying these specific requirements, the authors purpose the ''wake-sleep algorithm'', a two-phase procedure in which each network layer effectively learns representations of the activity in adjacent hidden layers. Here, the network is composed of feed-forward "recognition" connections used to generate an internal representation of the input, and feed-back generative connections used to produce an estimated reconstruction of the original input based on this learned internal representation. The goal is to learn an efficient representation which accurately characterizes the input to the system.
 
In considering general learning procedures, supervised methods for neural networks are limited in that they can only be executed in specifically-structured environments. For these systems to learn, the environment must be equipped with an external "teacher" providing the network with explicit feedback on its predictive performance. From there, the system needs a means for circulating this error information across the entire network, so that the weights can be adjusted accordingly. To apply neural networks in contexts not satisfying these specific requirements, the authors purpose the ''wake-sleep algorithm'', a two-phase procedure in which each network layer effectively learns representations of the activity in adjacent hidden layers. Here, the network is composed of feed-forward "recognition" connections used to generate an internal representation of the input, and feed-back generative connections used to produce an estimated reconstruction of the original input based on this learned internal representation. The goal is to learn an efficient representation which accurately characterizes the input to the system.
 +
 +
=Model Configuration=
 +
 +
<center>
 +
[[File:Network.png |frame | center |Fig 1. An illustration of the network structure. ]]
 +
</center>
 +
 +
To enforce the requirement that the network produces efficient reconstructions of the data, the cost function is selected by viewing the problem as a task of information transmission. The original input vector is to be indirectly communicated from the sender to the receiver via first sending the internal representation of the datum learned by the system, and then passing along the deviation of the original input from its approximation produced by the generative reconstruction of the internal representation.

Revision as of 17:08, 17 November 2015

Introduction

In considering general learning procedures, supervised methods for neural networks are limited in that they can only be executed in specifically-structured environments. For these systems to learn, the environment must be equipped with an external "teacher" providing the network with explicit feedback on its predictive performance. From there, the system needs a means for circulating this error information across the entire network, so that the weights can be adjusted accordingly. To apply neural networks in contexts not satisfying these specific requirements, the authors purpose the wake-sleep algorithm, a two-phase procedure in which each network layer effectively learns representations of the activity in adjacent hidden layers. Here, the network is composed of feed-forward "recognition" connections used to generate an internal representation of the input, and feed-back generative connections used to produce an estimated reconstruction of the original input based on this learned internal representation. The goal is to learn an efficient representation which accurately characterizes the input to the system.

Model Configuration

Fig 1. An illustration of the network structure.

To enforce the requirement that the network produces efficient reconstructions of the data, the cost function is selected by viewing the problem as a task of information transmission. The original input vector is to be indirectly communicated from the sender to the receiver via first sending the internal representation of the datum learned by the system, and then passing along the deviation of the original input from its approximation produced by the generative reconstruction of the internal representation.