Timeline for How can the sum of squared errors have negative gradient if it's defined as the squared of the error?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 10, 2021 at 17:55 | history | edited | nbro | CC BY-SA 4.0 |
deleted 5 characters in body
|
| Nov 25, 2018 at 17:17 | comment | added | Neil Slater | @Ben: In brief, the MSE is more used in stats-based learning algorithms than SSE because it estimates the loss for a single "typical" point, and the more data you get, the better the estimate. That means you can do things such as take a small subset (mini-batch) of your full data set, measure the loss, calculate the gradient and make a step - all the while using self-consistent (but noisy) measures of the errors and gradients. Also you can make comparisons easily between different sizes of data set. If that is not clear, please ask a new separate question. | |
| Nov 25, 2018 at 11:49 | comment | added | Ben | Nice, thanks for the clear and detailed answer. Just one more question: While the SSE is the sum of the errors of all samples, the MSE divides through the number of samples to get the mean error. But: The MSE makes far more sense in a NN, right? I mean, why should the error, and so the adjustment of the weights grow with the number of samples? | |
| Nov 25, 2018 at 9:47 | vote | accept | Ben | ||
| Nov 25, 2018 at 9:29 | history | edited | Neil Slater | CC BY-SA 4.0 |
added 2 characters in body
|
| Nov 25, 2018 at 9:11 | history | answered | Neil Slater | CC BY-SA 4.0 |