Timeline for Theta weight parameter zero initialization
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 30, 2017 at 22:59 | comment | added | Sam | I'm assuming when you say $\theta$, you mean the parameters. So yes, the optimization tries to minimize the error, but the gradient gives you a "good direction" for the next step. The only "really bad way" to initialize your optimization, is to initialize it somewhere where the gradient is close to 0, everywhere else the process will start going | |
| Aug 30, 2017 at 22:48 | comment | added | Char | But doesn't the cost/error affect what the gradient during optimization? | |
| Aug 30, 2017 at 22:37 | history | answered | Sam | CC BY-SA 3.0 |