Timeline for Stochastic gradient descent for neural networks with tied weights
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 9, 2017 at 21:50 | comment | added | Pugl | actually realized that it was correct before I edited it, at least in our solutions it is w_tied...hm, well.. | |
| Aug 8, 2017 at 19:35 | history | bounty ended | Pugl | ||
| Aug 8, 2017 at 19:35 | vote | accept | Pugl | ||
| Aug 8, 2017 at 19:32 | comment | added | nlml | The stochastic part is that you will pick data points at random. Unless you only have one [$x_1, x_2, x_3$] vector, then you'll just 'stochastically' pick that one over and over again. Have never heard of stochastically updating weights (although it could be useful it would probably just be inefficient) - all weights are always updated at every training step. | |
| Aug 8, 2017 at 19:17 | comment | added | Pugl | I corrected the notation, you are right. However, what is the stochastic part here? The point in SGD is that we do pick datapoints at random..so how does that translate here? | |
| Aug 8, 2017 at 18:46 | history | answered | nlml | CC BY-SA 3.0 |