6
votes
Should I choose a model with the smallest loss or highest accuracy?
You should choose the model A. The loss is just a differentiable proxy for accuracy.
That said, the situation should be examined in more detail. If the higher loss is due to the data term, examine ...
4
votes
Accepted
Should I choose a model with the smallest loss or highest accuracy?
You should note that both your results are consistent with a "true" probability of 87% accuracy, and your measurement of a difference between these models is not statistically significant. With an 87% ...
1
vote
how to decide the optimum model?
Testing each time on a test set is against the point of a train-val-test split. The reason test is important, is that you are only supposed to test on it when you think your model is good and ready ...
1
vote
Should I choose a model with the smallest loss or highest accuracy?
It depends on your application! Imagine a binary classifier that is always very "confident" - it always assigns P=100% to Class A and 0% to Class B, or vice versa (sometimes wrong, never uncertain!). ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
validation × 5deep-learning × 2
accuracy × 2
neural-networks × 1
machine-learning × 1
training × 1
long-short-term-memory × 1
prediction × 1
metric × 1
loss × 1
weights-initialization × 1
testing × 1
uncertainty-quantification × 1
test-datasets × 1
mnist × 1
validation-datasets × 1