Timeline for Is the Cross Entropy Loss important at all, because at Backpropagation only the Softmax probability and the one hot vector are relevant?
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 22, 2019 at 5:47 | comment | added | clemens_m_b | But how do we use the negative log likelihood in practice, because the derivative of the CEL is just the difference of the output probability and the one hot vector. The advantages of the logarithmical loss just vanish? | |
| Jul 20, 2019 at 7:22 | history | answered | ashukid | CC BY-SA 4.0 |