0

i dont understand if this learning curve had good learning rate or not. if I set lower bound to zero , it look like linear other wise it look little better, is this good/high/low learning rate ? Autoencoder , batch size 16 , learning rate : 3 e-5 , and loss function root mean square error Training sample : 20982 , validation samples : 5246

Improve this question
1
  • 1
    I don't think there's an answer. If you tested multiple learning rates and plotted the corresponding loss curves, it could've been possible to say the best learning rate (for your particular data, model and loss function) is the one whose loss curve is steepest. Here you have only one specimen, so I don't think it's possible to tell if it's a "good" or "bad" learning rate.
    – ForceBru
    Commented Nov 12, 2024 at 19:50
Related questions
1
Keras autoencoder : validation loss > training loss - but performing well on testing dataset
2
Deep autoencoder keeping constant accuracy in keras
3
Autoencoder learns average of all samples
Load 5 more related questions Show fewer related questions

0

Reset to default

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.