nerv - Lua-based toolkit for high-performance deep learning

	Commit message (Collapse)	Author	Age
*	do not use submodule for nerv-speech	Determinant	2015-08-06
\|
*	use expanded features and do global transf in embedding_example	Determinant	2015-08-05
\|
*	keep up with speech repo	Determinant	2015-08-05
\|
*	put global transformation into a separate library	Determinant	2015-08-05
\|
*	remove useless get_crit	Determinant	2015-06-25
\|
*	use the standard nerv error reporting in io lib	Determinant	2015-06-25
\|
*	separate non-Lua part of matrix code to a dedicated dir	Determinant	2015-06-24
\|
*	major change: use luarocks to manage project	Determinant	2015-06-22
\|
*	keep up with speech submodule	Determinant	2015-06-21
\|
*	change concept of ParamRepo; provide generalized param update; code ↵	Determinant	2015-06-20
\| \| \| \|	clean-up; #25 #26 #27 #29
*	...	Determinant	2015-06-06
\|
*	add profiling; add ce accurarcy; several other changes	Determinant	2015-06-05
\|
*	demo now works (without random shuffle)	Determinant	2015-06-03
\|
*	add ParamRepo, LayerRepo, DAGLayer	Determinant	2015-06-02
\|
*	add preprocessing layers and change layer constructor interface	Determinant	2015-06-02
\|
*	add expand_frm, rearrange_frm, scale_row	Determinant	2015-06-01
\|
*	move the destination of .so files to build/lib	Determinant	2015-05-30
\|
*	add submodule: speech (nerv-speech on github)	Determinant	2015-05-29