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

Distributed srm #220

Merged
merged 14 commits into from May 11, 2017

Conversation

Projects
None yet
3 participants
@mjanderson09
Contributor

mjanderson09 commented Apr 28, 2017

No description provided.

Show outdated Hide outdated brainiak/funcalign/srm.py
Show outdated Hide outdated brainiak/funcalign/srm.py
Show outdated Hide outdated tests/funcalign/test_srm.py

@mihaic mihaic requested a review from TuKo Apr 28, 2017

mjanderson09 added some commits May 1, 2017

@mihaic

This comment has been minimized.

Show comment
Hide comment
@mihaic

mihaic May 1, 2017

Contributor

Jenkins, retest this please.

Contributor

mihaic commented May 1, 2017

Jenkins, retest this please.

@mihaic

This comment has been minimized.

Show comment
Hide comment
@mihaic

mihaic May 2, 2017

Contributor

Jenkins, retest this please.

Contributor

mihaic commented May 2, 2017

Jenkins, retest this please.

@mihaic

mihaic approved these changes May 2, 2017

@TuKo

This comment has been minimized.

Show comment
Hide comment
@TuKo

TuKo May 2, 2017

Contributor

@mjanderson09 great job!
Please, consider adding the TS-SVD and TS-QR code as well. We should allow for reproducibility of the IEEE BigData algorithm. Also, all SRM flavors will benefit from it, and some other methods as well.

Don't need to do it now. You can do it in a different PR.

Thank you!

Contributor

TuKo commented May 2, 2017

@mjanderson09 great job!
Please, consider adding the TS-SVD and TS-QR code as well. We should allow for reproducibility of the IEEE BigData algorithm. Also, all SRM flavors will benefit from it, and some other methods as well.

Don't need to do it now. You can do it in a different PR.

Thank you!

mjanderson09 added some commits May 3, 2017

Show outdated Hide outdated tests/funcalign/test_srm.py
Show outdated Hide outdated tests/funcalign/test_srm.py
@mihaic

mihaic approved these changes May 10, 2017

@mihaic

This comment has been minimized.

Show comment
Hide comment
@mihaic

mihaic May 10, 2017

Contributor

@TuKo, what say you?

Contributor

mihaic commented May 10, 2017

@TuKo, what say you?

@TuKo

This comment has been minimized.

Show comment
Hide comment
@TuKo

TuKo May 10, 2017

Contributor

@TuKo says NIPS, sorry...

Contributor

TuKo commented May 10, 2017

@TuKo says NIPS, sorry...

mjanderson09 added some commits May 11, 2017

Show outdated Hide outdated tests/funcalign/test_srm.py
@mihaic

mihaic approved these changes May 11, 2017

@TuKo

This comment has been minimized.

Show comment
Hide comment
@TuKo

TuKo May 11, 2017

Contributor

👍 Great work!

Contributor

TuKo commented May 11, 2017

👍 Great work!

@TuKo

TuKo approved these changes May 11, 2017

@mihaic mihaic merged commit 3e039bd into brainiak:master May 11, 2017

3 checks passed

continuous-integration/travis-ci/pr The Travis CI build passed
Details
linux Build finished.
Details
macos Build finished.
Details
@mihaic

This comment has been minimized.

Show comment
Hide comment
@mihaic

mihaic May 11, 2017

Contributor

For the record, here is the effect of the changes on the accuracy in the image prediction example:

v0.4:
SRM: The average accuracy among all subjects is 0.657143 +/- 0.058576
Det. SRM: The average accuracy among all subjects is 0.657143 +/- 0.070891

master (i.e., per-subject random number generators):
SRM: The average accuracy among all subjects is 0.664286 +/- 0.076097
Det. SRM: The average accuracy among all subjects is 0.673214 +/- 0.068721

distributed_srm:
SRM: The average accuracy among all subjects is 0.664286 +/- 0.076097
Det. SRM: The average accuracy among all subjects is 0.673214 +/- 0.068721
Contributor

mihaic commented May 11, 2017

For the record, here is the effect of the changes on the accuracy in the image prediction example:

v0.4:
SRM: The average accuracy among all subjects is 0.657143 +/- 0.058576
Det. SRM: The average accuracy among all subjects is 0.657143 +/- 0.070891

master (i.e., per-subject random number generators):
SRM: The average accuracy among all subjects is 0.664286 +/- 0.076097
Det. SRM: The average accuracy among all subjects is 0.673214 +/- 0.068721

distributed_srm:
SRM: The average accuracy among all subjects is 0.664286 +/- 0.076097
Det. SRM: The average accuracy among all subjects is 0.673214 +/- 0.068721

danielsuo pushed a commit that referenced this pull request Nov 16, 2017

Added functionality for retrieving variables from control dependencies (
#220)

* Added test for retriving variables from an optimizer

* Added comments to test

* Addressed comments

* Fixed travis bug

* Added fix to circular controls

* Added set for explored operations and duplicate prefix stripping

* Removed embeded ipython

* Removed prefix, use seperate graph for each network

* Removed redundant imports

* Addressed comments and added separate graph to initializer

* fix typos

* get rid of prefix in documentation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment