search

ErikOsinga / master_research_project

Repository for the Master Research Project: "Data compression for weak lensing studies with the upcoming Euclid mission with Information Maximizing Neural Networks"
0 stars 0 forks source link

1D Gaussian with unknown mean and variance #4

Closed ErikOsinga closed 5 years ago

ErikOsinga commented 5 years ago

Probably better to test the networks capabilities on 2 parameters with a simpler example. Thus will define theta = [mu,sigma] and see if the network works on 1D Gaussian data

ErikOsinga commented 5 years ago

Seems the main problem was not using the ADAM optimizer. At the moment it is working quite well, if the learning rate is not too high. Now testing various different parameters.

ErikOsinga commented 5 years ago

After implementing 2D posterior plotting, I think we can close this issue. The latest result for this 1D Gaussian with unknown mean and variance is now:

variables_vs_epochs_1013

Which results in the following approximate 2D posterior, the blue lines mark the true values.

pmc_abc_1013_2d

This was achieved with the following modelsettings:

Version,Learning rate,Keep rate,num_epochs,n_train,delta_theta,number of simulations,fiducial θ,differentiation fraction,input shape,number of summaries,calculate MLE,prebuild,save file,wv,bb,activation,α,hidden layers,Final detF train,Final detF test

1013,1e-05,0.6,10000,1,[0.1 0.1],10000,[0. 1.],0.05,[10],2,True,True,Models/data/model1013,0.0,0.1,leaky_relu,0.01,"[256, 256, 256]",47.37,42.19

mjvakili commented 5 years ago

Excellent! closing this issue