Skip to main content
Cross Validated

Return to Answer

replaced vague 'value' with 'delta'
Source Link
Idr
Idr
  • 759
  • 1
  • 6
  • 14

In each iteration of your backpropagation algorithm, you will update the weights by multiplying the existing weight by a valuedelta determined by backpropagation. If the initial weight value is 0, multiplying it by any value for delta won't change the weight which means each iteration has no effect on the weights you're trying to optimize.

In each iteration of your backpropagation algorithm, you will update the weights by multiplying the existing weight by a value determined by backpropagation. If the initial weight value is 0, multiplying it by any value won't change the weight which means each iteration has no effect on the weights you're trying to optimize.

In each iteration of your backpropagation algorithm, you will update the weights by multiplying the existing weight by a delta determined by backpropagation. If the initial weight value is 0, multiplying it by any value for delta won't change the weight which means each iteration has no effect on the weights you're trying to optimize.

Source Link
Idr
Idr
  • 759
  • 1
  • 6
  • 14

In each iteration of your backpropagation algorithm, you will update the weights by multiplying the existing weight by a value determined by backpropagation. If the initial weight value is 0, multiplying it by any value won't change the weight which means each iteration has no effect on the weights you're trying to optimize.