Abstract for wu_tr124

Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR124


Lizhong Wu and Mahesan Niranjan

April 1993

In this report, we present analysis and prediction of building data using recurrent neural nets. We first explain why a recurrent neural net is chosen by analysing the static and dynamic characteristics of the data, and demonstrating its prediction result. Two techniques are then developed to track the non-stationary state and to catch the long-term memory structure of the data to improve the prediction performance, which cannot be attained with a large recurrent net due to its training difficulty.

(ftp:) wu_tr124.ps.Z (http:) wu_tr124.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) wu_tr124.pdf | (http:) wu_tr124.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.