Richard Crowder
Richard Crowder
Not pickup up RPi since yourself and Matt had a stab last. Keeping an eye on it, and related issues. Something else maybe for the challenge event. But tricky finding...
@breznak Do you have a branch link for your work so far?
(If required) Looks like Eigen can be tested here; http://docs.biicode.com/c++/examples/eigen.html
Also, https://github.com/hexahedria/biaxial-rnn-music-composition http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/
@floybix Could this be related to pre-synaptic inhibition. Reading Spratling an co.'s work on "Pre-integration lateral inhibition enhances unsupervised learning", for example. Or Fergal's pre-pooler feedback twist? http://www.inf.kcl.ac.uk/staff/mike/publications.html
@zdx3578 You could try running with the GNU debugger (gdb). You would need to rebuild the pge using the commands `cmake -DCMAKE_BUILD_TYPE=Debug .` followed by `make clean; make` and then...
Update: I quickly tried a debug version of the PGE on a headless Ubuntu AWS EC2 instance, and faced an issue with SFML Window library. This was seen using gdb...
Thanks. This AttributeError happens when the PGE process fails to start properly. Investigation into this issue on EC2 show that it's likely an issue with SFML not being able to...
@breznak I'm not sure what the point would be to lock this repo into a pip install-able state, as opposed to git cloning it. In the future I can imagine...
@breznak I tried last weekend to get this as a submodule of nupic. But couldn't get it work. I'll have another look this weekend.