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

2 visualizaciones (últimos 30 días)

David Franco el 28 de Dic. de 2020

0
Enlazar

Enlace directo a esta pregunta

https://la.mathworks.com/matlabcentral/answers/704202-why-is-the-neural-network-training-slow-when-i-don-t-use-the-matlab-toolbox

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...

0 comentarios
Mostrar -2 comentarios más antiguosOcultar -2 comentarios más antiguos

Iniciar sesión para comentar.

Iniciar sesión para responder a esta pregunta.

Respuestas (0)

Iniciar sesión para responder a esta pregunta.

Categorías

AI, Data Science, and Statistics Deep Learning Toolbox Function Approximation, Clustering, and Control Function Approximation and Clustering Define Shallow Neural Network Architectures

Más información sobre Define Shallow Neural Network Architectures en Help Center y File Exchange.

Productos

MATLAB

Versión

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by