Skip to main content
11 events
when toggle format what by license comment
Jan 4, 2022 at 19:44 answer added Jay Ekosanmi timeline score: 1
Jan 4, 2022 at 19:37 comment added Sycorax It's not necessarily the kind of subjective question that is discouraged on Stack Exchange, but it does make the question incomplete. Knowing the answer to "Does my neural network fit well?" requires information that only you have: "Do the predictions from this model solve my problem?"
Jan 4, 2022 at 19:32 comment added silent_hunter So I think that this opinion is so general and don't give answer about above question
S Jan 4, 2022 at 19:29 review Reopen votes
Jan 4, 2022 at 19:31
S Jan 4, 2022 at 19:29 history reopened Avraham
Sycorax
Jan 4, 2022 at 19:25 history left closed in review whuber Original close reason(s) were not resolved
Jan 4, 2022 at 19:23 review Reopen votes
Jan 4, 2022 at 19:25
Jan 4, 2022 at 19:22 history edited silent_hunter CC BY-SA 4.0
added 91 characters in body Added to review
Jan 4, 2022 at 19:20 history closed Sycorax Needs details or clarity
Jan 4, 2022 at 19:18 comment added Sycorax I think you forgot to attach the plots that you're referring to. In any event, machine learning and statistical models don't exist in a vacuum. The relevant question isn't "is my loss value good?", but instead "is my model good enough for my particular application?" When the model makes mistakes (which it will, inevitably), you want to know if the costs of those mistakes are outweighed by the value of its correct predictions.
Jan 4, 2022 at 19:16 history asked silent_hunter CC BY-SA 4.0