Skip to content

Corrected dAL and used linear_activation_backward() #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Corrected dAL and used linear_activation_backward() #11

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions Neural Networks and Deep Learning/Building your Deep Neural Network - Step by Step.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1231,23 +1231,21 @@
" \n",
" # Initializing the backpropagation\n",
" ### START CODE HERE ### (1 line of code)\n",
" dAL = dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))\n",
" dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))\n",
" ### END CODE HERE ###\n",
" \n",
" # Lth layer (SIGMOID -> LINEAR) gradients. Inputs: \"AL, Y, caches\". Outputs: \"grads[\"dAL\"], grads[\"dWL\"], grads[\"dbL\"]\n",
" ### START CODE HERE ### (approx. 2 lines)\n",
" current_cache = caches[-1]\n",
" grads[\"dA\" + str(L)], grads[\"dW\" + str(L)], grads[\"db\" + str(L)] = linear_backward(sigmoid_backward(dAL, \n",
" current_cache[1]), \n",
" current_cache[0])\n",
" grads[\"dA\" + str(L-1)], grads[\"dW\" + str(L)], grads[\"db\" + str(L)] = linear_activation_backward(dAL, current_cache, activation="sigmoid")\n",
" ### END CODE HERE ###\n",
" \n",
" for l in reversed(range(L-1)):\n",
" # lth layer: (RELU -> LINEAR) gradients.\n",
" # Inputs: \"grads[\"dA\" + str(l + 2)], caches\". Outputs: \"grads[\"dA\" + str(l + 1)] , grads[\"dW\" + str(l + 1)] , grads[\"db\" + str(l + 1)] \n",
" ### START CODE HERE ### (approx. 5 lines)\n",
" current_cache = caches[l]\n",
" dA_prev_temp, dW_temp, db_temp = linear_backward(sigmoid_backward(dAL, caches[1]), caches[0])\n",
" dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(L-1)], current_cache, activation="relu")\n",
" grads[\"dA\" + str(l + 1)] = dA_prev_temp\n",
" grads[\"dW\" + str(l + 1)] = dW_temp\n",
" grads[\"db\" + str(l + 1)] = db_temp\n",
Expand Down