new neural net implementation for TMVA#104
Closed
re-cursion wants to merge 159 commits into
Closed
Conversation
new file: tmva/inc/TMVA/MethodNN.h new file: tmva/inc/TMVA/Monitoring.h new file: tmva/inc/TMVA/NeuralNet.h new file: tmva/inc/TMVA/NeuralNet_i.h new file: tmva/inc/TMVA/Pattern.h modified: tmva/inc/TMVA/Types.h new file: tmva/src/MethodNN.cxx new file: tmva/src/NeuralNet.cxx
added stochastic to the gradient descent modified: tmva/inc/TMVA/NeuralNet_i.h
modified: tmva/tmva/inc/TMVA/NeuralNet.h modified: tmva/tmva/inc/TMVA/NeuralNet_i.h modified: tmva/tmva/src/MethodNN.cxx modified: tmva/tmva/src/NeuralNet.cxx
modified: ../tmva/inc/TMVA/Monitoring.h modified: ../tmva/inc/TMVA/NeuralNet_i.h modified: ../tmva/src/MethodNN.cxx modified: ../tmva/src/NeuralNet.cxx
…alue" modified: ../tmva/src/MethodNN.cxx
- fixed progress computation modified: ../tmva/inc/TMVA/NeuralNet_i.h modified: ../tmva/src/MethodNN.cxx
modified: ../../tmva/tmva/inc/TMVA/NeuralNet.h modified: ../../tmva/tmva/inc/TMVA/NeuralNet_i.h modified: ../../tmva/tmva/src/MethodNN.cxx put some basic usage into the examples modified: TMVAClassification.C
modified: tmva/tmva/inc/TMVA/NeuralNet_i.h
- added possibility to define the dropout fraction for each layer individually
modified: tmva/inc/TMVA/NeuralNet.h modified: tmva/inc/TMVA/NeuralNet_i.h modified: tmva/src/MethodNN.cxx modified: tmva/src/NeuralNet.cxx
- add multithreading as an option for the NN in TMVA
put in "preTraining". But no settings to turn it on yet.
- add multithreading as an option for the NN in TMVA
put in "preTraining". But no settings to turn it on yet.
… values for truth in pattern
Member
|
The new Deep NN is now committed in the master via the new pull request by Omar Lorenzo |
Closed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
10 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implementation of a new neural network for TMVA which contains recent developments in the field of neural networks (e.g. weight initialization [Gerlot], SGD, Hogwild style multithreading, drop-out, momentum). It allows for multithreaded training.