Timeline for Why is no activation function needed for the output layer of a neural network for regression?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 11, 2021 at 11:09 | comment | added | nbro | @Kokodoko Yes, this can happen, but the weights should converge to some reasonable values, once you optimize the objective function. Moreover, you can also limit the weights and activations e.g. by using specific activation functions that squash the inputs to the neurons to certain ranges, which is your case (in that example, they are using the sigmoid in the hidden layer, which squashes the inputs to the range [0, 1]). You can also have regularization of the weights, to make them small. | |
| Mar 11, 2021 at 11:03 | comment | added | Kokodoko | Thanks for the explanation. But if the weights in a neural network can be any number, won't the output also vary wildly? Miles per gallon should be a value of around 20 to 100 for example, but if the random weight is 2.000.000, won't you get a crazy output? | |
| Mar 11, 2021 at 11:01 | vote | accept | Kokodoko | ||
| Mar 11, 2021 at 10:20 | history | answered | nbro | CC BY-SA 4.0 |