Skip to content

Fixed formally wrong backpropagation/gradient descent #3

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

Fixed formally wrong backpropagation/gradient descent #3

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: 5 additions & 3 deletions nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,13 @@
nr_correct += int(np.argmax(o) == np.argmax(l))

# Backpropagation output -> hidden (cost function derivative)
delta_o = o - l
w_h_o += -learn_rate * delta_o @ np.transpose(h)
b_h_o += -learn_rate * delta_o
delta_o = (o - l)*o*(1-o)

# Backpropagation hidden -> input (activation function derivative)
delta_h = np.transpose(w_h_o) @ delta_o * (h * (1 - h))
#update weights
w_h_o += -learn_rate * delta_o @ np.transpose(h)
b_h_o += -learn_rate * delta_o
w_i_h += -learn_rate * delta_h @ np.transpose(img)
b_i_h += -learn_rate * delta_h

Expand Down