-
Notifications
You must be signed in to change notification settings - Fork 178
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
please explain your conclusion that TS deep NN transformers performance are bad #422
Comments
Not sure specifically which statements you are referring to - can you cite them explicitly and point them out (timestamp) in the video? |
Hi, just wanted to follow up on this. Do you have any questions that we can answer? I think there have been many attempts at Transformers for time series, some succesful, some less so. This also depends on how you define success (e.g. accuracy, model complexity, model size). Hence, both conclusions that you state can be made, but again, not sure what specific statement it is you are referring to. |
Closing, but feel free to re-open if you have further questions. |
main question is about accuracy |
Happy to answer a question about accuracy - can you please make your question specific - which models, what problem setting, which experiments, what were the results. The only valid answer to a generic (vague) question such as 'Is Transformers better than an ML model for forecasting' is 'it depends'. Not sure this is the answer you're seeking, but absent any relevant context this is the only valid answer. |
as I wrote above 2 weeks ago "main question is about accuracy" may you explain your statement that transformers performance are bad per from one hand you confirm your conclusion that TS deep NN transformers performance are bad from another hand you say |
Could you point to where in the video we make these specific statements? It feels we're going around in circles with this. I've asked the above clarifying question at the beginning too. I can't answer vague non-specific questions. Unless you're willing to offer me any help in actually understanding what it is you are asking, the explanation will be: 'it depends, both statements can be true, it depends on the context'. |
great job thanks
please explain your conclusion that TS deep NN transformers performance are bad
may you clarify what this your video
https://youtu.be/r43JnfHrmJk?t=913
from one hand you confirm your conclusion that TS deep NN transformers performance are bad
from another hand you say
you developed ML model which uses TS deep NN transformers and it is very good
The text was updated successfully, but these errors were encountered: