Skip to content
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.

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

issue332 - add intercept term to softmax regression #418

Merged
merged 1 commit into from Mar 5, 2015

Conversation

apir8181
Copy link
Contributor

@apir8181 apir8181 commented Mar 5, 2015

In issue332, data points from Gaussian distribution (base [1, 1, 1]) and points from base [9, 9, 9] can't not be well separating using softmax regression. The implementation of softmax regression haven't add the intercept term, which means the hypothesis space only contains 3-d planes crossing the origin. This patch try to fixed this problem by adding the intercept term to it.

rcurtin added a commit that referenced this pull request Mar 5, 2015
issue332 - add intercept term to softmax regression
@rcurtin rcurtin merged commit 50fe869 into mlpack:master Mar 5, 2015
@rcurtin
Copy link
Member

rcurtin commented Mar 5, 2015

Awesome, this looks great. Thanks! Now we can release softmax regression with the next release.

@rcurtin rcurtin added this to the mlpack 1.1.0 milestone Mar 5, 2015
rcurtin added a commit that referenced this pull request Mar 6, 2015
issue332 - add intercept term to softmax regression
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants