Initialize weights and biases in a nureal network

4 Ansichten (letzte 30 Tage)
Pouya Jamali
Pouya Jamali am 19 Dez. 2011
How can i initialize weights and biases in a feed forward neural network which built with newff command to arbitrary values before training?

Akzeptierte Antwort

Greg Heath
Greg Heath am 20 Dez. 2011
The call to NEWFF automatically creates random initial weights via INITNW. Just remember to initialize RAND before the first call to NEWFF so that you can duplicate your results.
Greg

Weitere Antworten (0)

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Help Center und File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by