michaelhush/M-LOOP

Merge pull request #17 from michaelhush/revert-16-NeuralNetA …

Revert "Get NN working a bit better on the tests"

Revert "Get NN working a bit better on the tests"

charmasaur committed on GitHub Dec 9, 2016

All checks have passed

2 successful checks

continuous-integration/travis-ci/pr — The Travis CI build passed

Details

continuous-integration/travis-ci/push — The Travis CI build passed

Details

Merge pull request #16 from charmasaur/NeuralNetA …

Get NN working a bit better on the tests

Plot NN surface when there are 2 params

Use TF gradient when minimizing NN cost function estimate

Still print predicted_best_cost even when predicted_best_uncertainty … …

…isn't set

Tweak some NNI params to perform better on the test

Don't do one last train in order to predict minima …

at the end. This was causing an exception to be thrown when trying to
get costs from the queue.

Add (trivial) scaler back to NNL

Set new_params_event in MLC after getting the cost …

When generation_num=1, if the new_params_event is set first then the
learner will try to get the cost when the queue is empty, causing an
exception.

Dumb implementation of predict_costs array version

Pull NNI construction into create_neural_net

Merge branch 'NeuralNetA' of https://github.com/michaelhush/M-LOOP in… …

…to NeuralNetA

Conflicts:
	mloop/controllers.py
	mloop/learners.py

Fix importing/creation of NN impl …

We need to specify nnlearner as a package. More subtly, because of TF
we can only run NNI in the same process in which it's created. This
means we need to wait until the run() method of the learner is called
before constructing the impl.

Tidying/logging for NN impl

Remove scaler from NNController

More NNController tidying/tweaking

Fix number_of_controllers definition

Basic NN learner implementation …

I've pulled the actual network logic out into a new class, to
keep the TF stuff separate from everything else and to keep a
clear separation between what's modelling the landscape and
what's doing prediction.

Fix some NN typos

Remove unnecessary uncertainty stuff from NNL

Tweaks to NN learner shell

Fix some minor controller documentation errors

Fix some whitespace errors …

Git complains to me about them when I touch nearby lines, so I figured
it was easier just to fix them.

Fix setup syntax error

Tweaks to tutorials documentation