Optimization of the hidden unit function
β
Osamu Fujita
π
Article
π
1992
π
Elsevier Science
π
English
β 790 KB
A novel objective fimction is proposed.for optimizing the hidden unit function in feedforward neural networks. This objective fiznction represents the performance of the hidden unit at minimizing the least squared output errors of the linear output zmit. This is derived from the decrease in the outp