Fernando Guimarães Ferreira

Well, I have two classes, that can be mapped in a single neuron (Outputs -1 and 1), so I don't think there is a problem on this point. The Precision...

Thanks!! It helped a lot =) On the same idea, is there any algorithm that accepts different objectives? I am trying to develop the beta-divergence for a NMF multiplicative method...

the imap i would like to disable (or change) would be i î *@:call AutoPairsJump()a i ð *@AutoPairsToggle() i â *@=AutoPairsBackInsert() i å *@=AutoPairsFastWrap() How do I do it?

Ok! progress!! Now I can type â on vim but can't write on Macvim gui. vim --version VIM - Vi IMproved 7.4 (2013 Aug 10, compiled May 11 2015 05:04:13)...

In the end, the only thing that helped was unbundle autopairs

Hello, I'am facing similar problem ``` [undouble] >INFO> [171595] images are extracted. [undouble] >INFO> Reading and checking images. [undouble] >INFO> Reading and checking images. [clustimage]: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 171595/171595 [38:40 Compute adjacency...

Ok, I've made some digging and I guess the problem is with numpy. It seems, the != operator change its behaviour from element-wise operator to full object comparision for large...