Abstract P-002

002 Jurkovic.p65

002 Nikoli..p65

!" ! #$ % &$ $!' ( " # )$!& * % & ! + , * # + # &! + !& , . / ) ) 0 )$ " !#$& * # ) " ( !& * % & ! ) , *! ) $ & ' (* 1 )' " . )$ 223 , * $3 #)$! 4 !' !$ ', # % 1 # " 1 $% % " & 4 $ " # )$!& 0& !' * ! * % & ! + , * # ! + # &! % # * % ( & % $ $5 . ) %6 " 1 $% % 5 #$ $ ' &' $ " # )$!& &$ , ( 5 ) % # !& ' , * # % 37 $8'& %$% % , * # ) !$ 1 #$ " !$1 ', % ) !& '& ) + ). 1 , & ) + 1 &$ ) 4 ) !' 4 # 4 ...

GCNU TR 1999 – 002 Linear

This note gives a closed form expression for the linear transform computed by an optimally trained linear heteroencoder network of arbitrary topology trained to minimize squared error. The transform can be thought of as a restricted rank version of the basic linear least-squares regression (discrete Wiener filter) between input and output. The rank restriction is set by the “bottleneck” size of...

abstract

ABSTRACT