The number one thing to keep in mind about machine learning is that performance is evaluated on samples from one dataset, but the model is used in production on samples that may not necessarily follow the same characteristics...
Show this thread
-
If every possible situation is known and you want to prioritize scalability and cost-reduction, go with the model. Models exist to encode and operationalize human cognition in well-understood situations.
Show this thread
("well understood" meaning either that it can be explicitly described by a programmer, or that you can amass a dataset that densely samples the distribution of possible situations -- which must be static)
-
-
For medical decease prediction, detection of say cancer of a human organ& say we have classes 1) No cancer 2) cancerous 3) Uncertain. If DNN model is created based on decent training & validation data set sizes, is this not sufficient?
-
We do not want True as False (i.e. cancer as no cancer) output. In case of 2 & 3 outputs, a radiologist or doctor is going to sure see images/data. In case of Case 1, if there is facility to transmit all case 1 data to software manufacturer to validate, is it not sufficient?
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.