Using Recurrent Networks for Dimensionality Reduction

Title: en_US Using Recurrent Networks for Dimensionality Reduction
Creator: en_US Jones, Michael J.
Date: 2004-10-20T20:23:37Z
Date Available: 2004-10-20T20:23:37Z
Date Issued: en_US 1992-09-01
Identifier: en_US AITR-1396
uri: http://hdl.handle.net/1721.1/7045
Abstract: en_US This report explores how recurrent neural networks can be exploited for learning high-dimensional mappings. Since recurrent networks are as powerful as Turing machines, an interesting question is how recurrent networks can be used to simplify the problem of learning from examples. The main problem with learning high-dimensional functions is the curse of dimensionality which roughly states that the number of examples needed to learn a function increases exponentially with input dimension. This thesis proposes a way of avoiding this problem by using a recurrent network to decompose a high-dimensional function into many lower dimensional functions connected in a feedback loop.
Extent: 2167097 bytes; 1325986 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1396