Skip to content

Corrected log-likelihood loss function #6

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 2 commits into
base: master
Choose a base branch
from
Open

Corrected log-likelihood loss function #6

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b006d22
Corrected log-likelihood loss function
Kanav123 Dec 26, 2016
353e52f
Added nan_to_num in log likelihood loss function
Kanav123 Dec 26, 2016
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
4 changes: 2 additions & 2 deletions neuralnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ def cross_entropy_loss(a, y):
return np.sum(np.nan_to_num(-y*np.log(a)-(1-y)*np.log(1-a)))

def log_likelihood_loss(a, y):
return -np.dot(y, softmax(a).transpose())
return -np.nan_to_num(np.log(np.dot(y, softmax(a).transpose())))

def delta(a, y):
""" delta for both activations works out to be the same"""
Expand All @@ -97,4 +97,4 @@ def derivative(z, fn):
f = sigmoid
elif fn == SOFTMAX:
f = softmax
return f(z)*(1-f(z))
return f(z)*(1-f(z))