Number of epochs not reached in anfisedit

3 visualizaciones (últimos 30 días)
Vinicius
Vinicius el 13 de Dic. de 2022
Respondida: Harsh Sanghai el 23 de Mzo. de 2023
When using anfisedit tool in Matlab I put the epochs number in 6, for example, however every time I train the model it only trains it 2 times, not 6 as previously stated. What could be the problem?

Respuestas (1)

Harsh Sanghai
Harsh Sanghai el 23 de Mzo. de 2023
Hi,
If you are observing that the model is only trained for 2 epochs instead of 6, there might be several reasons for this behavior. Here are a few things you can check:
  1. Check the convergence criteria: ANFIS stops training when the error between the predicted output and the actual output falls below a certain threshold or when the maximum number of epochs is reached. Check the convergence criteria to ensure that the training is not stopping prematurely due to the error threshold being met before 6 epochs.
  2. Check the training dataset: Ensure that the training dataset is large enough to require more than 2 epochs of training. If the training dataset is small, the algorithm may converge quickly, resulting in fewer epochs of training.
  3. Check the ANFIS settings: Double-check that you have set the correct "epochs" parameter in the ANFIS settings. Additionally, ensure that other ANFIS parameters, such as the number of membership functions, are set appropriately.
  4. Check for errors: Check the output and error messages in the MATLAB console to see if there are any error messages that may explain why the training is stopping earlier than expected.

Categorías

Más información sobre Fuzzy Logic Toolbox en Help Center y File Exchange.

Productos


Versión

R2022a

Community Treasure Hunt

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

Start Hunting!

Translated by