DLFS_code icon indicating copy to clipboard operation
DLFS_code copied to clipboard

Typo in 02_fundamentals/Code.ipynb

Open ScytheMax opened this issue 4 years ago • 0 comments

Dear Mr. Weidman,

I am currently trying to understand the code in [45], the function "loss_gradients".

I just want to ask, if in the line loss_gradients['B1'] = dLdB1.sum(axis=0)

it should be written instead: loss_gradients['B1'] = dLdB1

Reason: The expression dLdB1 in my test project shows me, that the dimension of it is (hidden_size,1). Also the dimension of weights['B1'] is (hidden_size,1). If the expression additonally sum over all [hidden_size] entries, then each [hidden_size] entry of weights['B1'] is updated with the same value. That seems not correct for me.

Best Regards

ScytheMax avatar Feb 07 '21 11:02 ScytheMax