cs231n

cs231n copied to clipboard

svm_loss_vectorized Derivative

1

https://github.com/naya0000/cs231n/blob/e1192dc8cbaf078c3cfb691e12b8d6d2ec40c8fa/assignment1/cs231n/classifiers/linear_svm.py#L110 Can someone explain why this subtraction is done? An explanation for derivative calculation.

mmuneeburahman

can not get the relative error which is less than e-3.

14

I am learning the Transformer_Captioning.ipynb in assignment3. After I run the cell of testing MultiHeadAttention, I get some incorrect results: ``` self_attn_output error: 0.449382070034207 masked_self_attn_output error: 1.0 attn_output error: 1.0...

ge1mina023

softmax_loss derivative -1 subtraction

2

Here is a partial derivative jacobian matrix for softmax:  This simplifies to:  ``` softmax[y[i]] -= 1 # update for gradient ``` Didn't get this? Can someone explain? For...

mmuneeburahman

"two_layer_net.ipynb" Solver section default setting problem

1

I have encounterd isues when tring to run the solver in default learning rate 1e-2, when looking for other people's answers, I notice that everyone basically change it to 1e-3...

HumbleHumbert