Timeline for Danger of setting all initial weights to zero in Backpropagation
Current License: CC BY-SA 3.0
3 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Aug 19, 2020 at 21:26 | comment | added | Tahlor | Suppose every node has the same input weights. Then every node in a given layer has the same activation (output value). Then every node in a given layer gets the same weight updates. So the weights are still the same after each update. Adding an additional node in a given layer is then equivalent to having just 1 node in that layer and multiplying the weights by a constant. | |
Aug 19, 2020 at 19:22 | comment | added | Charlie Parker | why is " for any particular hidden layer all the nodes in this layer would have exactly the same inputs and would therefore stay the same as each other." true? | |
Dec 28, 2017 at 7:21 | history | answered | Austin | CC BY-SA 3.0 |