I'm current testing a model for spiral data. After 500 epoches, loss is 0.04 but the result is still unmatch with some part of the training data. (bottom left)


The model has 2 hidden tanh x 16 units running with ml5.js. I choose tanh because it seems to be smoother than ReLU. Apart from that they're the same.

Is this thing caused by the model or by ml5 itself?

  • $\begingroup$ It must be for ML5. The data work fine in TFJS. $\endgroup$ – uahnbu Mar 9 at 11:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.