/[gzz]/gzz/Documentation/Manuscripts/Paper/paper.tex
ViewVC logotype

Diff of /gzz/Documentation/Manuscripts/Paper/paper.tex

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.158 by tjl, Sun Dec 1 11:42:01 2002 UTC revision 1.159 by tjl, Sun Dec 1 11:43:10 2002 UTC
# Line 361  We make the assumption Line 361  We make the assumption
361  that at some point,  that at some point,
362  the results from the  different feature detectors,  the results from the  different feature detectors,
363  such as local and global shapes and colors,  such as local and global shapes and colors,
364  combine to form an abstract \emph{feature vector}  are combined to form an abstract \emph{feature vector}
365  (see Fig.~\ref{fig-perceptual}).  (see Fig.~\ref{fig-perceptual}).
366  This feature vector is then used as an input to the  The to compute which concept the particular
 networks which compute which concept the particular  
367  input corresponds to, in a simple perceptron-like  input corresponds to, in a simple perceptron-like
368  fashion\cite{rosenblatt62neurodynamics,widrow60adaptive}.  fashion\cite{rosenblatt62neurodynamics,widrow60adaptive}.
369  This is a configuration sometimes used in neural computation.  This is a configuration sometimes used in neural computation.
370    
371    
372  From this  From this
373  rough, qualitative model of visual perception  rough, qualitative model
374  we can formulate the following points:  we can formulate the following points:
375  To be distinguishable, \label{secfeaturevec}  To be distinguishable, \label{secfeaturevec}
376  \begin{itemize}  \begin{itemize}

Legend:
Removed from v.1.158  
changed lines
  Added in v.1.159

savannah-hackers-public@gnu.org
ViewVC Help
Powered by ViewVC 1.1.26