VNC Server conflicts with miniconda libs

Be sure to manipulate LD_LIBRARY_PATH

MATLAB on OSX

Install the old, Apple provided Java SE 6

Make sure JDK 8 is not installed like so

sudo rm -rf /Library/Java/JavaVirtualMachines/jdk<version>.jdk
sudo rm -rf /Library/PreferencePanes/JavaControlPanel.prefPane
sudo rm -rf /Library/Internet\ Plug-Ins/JavaAppletPlugin.plugin
sudo rm -rf /Library/LaunchAgents/com.oracle.java.Java-Updater.plist
sudo rm -rf /Library/PrivilegedHelperTools/com.oracle.java.JavaUpdateHelper
sudo rm -rf /Library/LaunchDaemons/com.oracle.java.JavaUpdateHelper.plist
sudo rm -rf /Library/Preferences/com.oracle.java.Helper-Tool.plist

 
https://support.apple.com/kb/DL1572?locale=en_US

http://www.mathworks.com/matlabcentral/answers/160070-how-do-i-install-r2013a-student-on-yosemite

https://discussions.apple.com/thread/6163798

VNC Tidbits

vncconfig -iconic &

after server is running on a machine to copy and paste out of VNC terminal

Add git-gui alias for OSX and brew

Add the following line to ~/.bashrc (version subject to change...)

alias gui="sh -c '/usr/local/Cellar/git/2.3.3/libexec/git-core/git-gui'"       

Cocktail Party

IFT6266 Summary

In summary, convolutional VAE and batch normalization seem very useful for fast training of VAE models for image data. Unfortunately there appear to be some Theano related issues with the current implementation of batch normalization, which cause the generated computation graph to ~100x slower for the convolutional version than the feedforward version. Eventually the convolutional version should be very efficient, but for now training times of two or three days are not as useful as the 40 minute training times for the feedforward model.

Semi-supervised VAE is also a very promising avenue for learning better generative models, but implementing the model proposed earlier will take time after the course is over. For now, all the code remains posted at https://github.com/kastnerkyle/ift6266h15 , with improvements to both batch normalization and the convolutional model, and soon semi-supervised VAE.

IFT6266 Week 11

Adding rescaling rmsprop with nesterov momentum as the optimizer, instead of sgd with nesterov, has proved to be quite valuable. The feedforward model now trains to "good sample" level within about 45 minutes. The current code is here https://github.com/kastnerkyle/ift6266h15

However, the convolutional model takes 3 days! Something might be wrong...


Original:

Samples from the feedforward model:

Reconstructions from feedforward:

Original:

Samples from the convolutional model:

Reconstructions from the convolutional model: