Why is the Neural Network training slow when I don't use the Matlab Toolbox?

6 views (last 30 days)
I am trying to optimize neural weights using the standalone Levenberg-Marquard algorithm, but the ANN training is much slower than when using the same algorithm in the Toolbox (trainlm). What causes this?
Standalone Levenberg-Marquard = 30 minutes
trainlm = 5 seconds
Same final accuracy...

Answers (0)

Community Treasure Hunt

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

Start Hunting!

Translated by