New answers tagged

1 vote

Best Error Function for Areas with Larger Slopes

The first idea to come to mind is: $$ \sum_{i=1}^n \bigg[\big(y_i-\hat y_i\big)^2 + \bigg\vert\dfrac{ d\hat y }{ dx }\bigg\vert \big(y_i-\hat y_i\big)^2 \bigg] $$ This gives you the regular square ...
user avatar
  • 33.4k
1 vote

Adjust results for a systematic error

You can create many, say $n$, test samples, each of size e.g. 500, like yours, and measure the error for each of them. This gives you a sample of size $n$ of your systematic error and from that, you ...
user avatar
  • 6,248
0 votes
Accepted

Absence and presence of uncertainties in a data

It looks like the uncertainties are reported out to two decimal places. If the uncertainty is so small that rounding to two decimal places gives zero, then I could see why they might choose against ...
user avatar
  • 33.4k
2 votes

Term for the error in machine learning as a direct result of incorrectly labelled data?

Answered in comments by Sycorax: This is sometimes called "label noise," the acknowledgement that the labels themselves may be incorrect (for any reason, including human error).
1 vote

Finding true error between two curves

The "total error" you are looking for may be something like the distance between functions. You are currently computing: $$error = \Sigma (f(x_i) -g(x_i))^2 $$ This will, as you have found, ...
user avatar
  • 113

Top 50 recent answers are included