Corrigendum to "BYY learning, regularized implementation, and model selection on modular networks with one hidden layer of binary units" [Neurocomputing 51 (2003) 277-301]

Corrigendum Corrigendum to " BYY learning, regularized implementation, and model selection on modular networks with one hidden layer of binary units " The author wishes to make the following corrections: On page 281, the line after Eq. (3): " densities both p(u); q(u) " should be " densities, where both p(u); q(u) are ". On page 285, the ÿrst line of Eq. (20): " y '; t = y ' (x t) " should be " y t; ' = y ' (x t) ". On page 286, the ÿrst line: " (b) comes from (b) " should be " (d) comes from (a) ". On page 287, in the last equation: t; 't should be t; '. On page 288, Step 1 in Table 1: The positions of " BI-architecture " and " B-architecture " should be switched.