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

	Commit message (Expand)	Author	Age
*	RNN support multiple input & fix network flush bug	Qi Liu	2016-03-17
*	add mask on softmax_ce	Qi Liu	2016-03-15
*	speedup duplicate layer	Qi Liu	2016-03-15
*	fix bug of dropout	Qi Liu	2016-03-11
*	update diagonlal lstm	Qi Liu	2016-03-11
\|\
\| *	fix bug	Qi Liu	2016-02-24
\| *	fix typo	Qi Liu	2016-02-24
\| *	update LSTM layer	Qi Liu	2016-02-24
* \|	add recipe and fix bugs	Qi Liu	2016-03-11
* \|	adapt asr_trainer.lua to new architecture	Determinant	2016-03-11
* \|	Merge branch 'master' of https://github.com/liuq901/nerv into liuq901-master	Determinant	2016-03-11
\|\ \
\| * \|	update lstm	Qi Liu	2016-03-04
\| * \|	update add_prefix for graph layer	Qi Liu	2016-03-03
\| * \|	fix bug	Qi Liu	2016-03-02
\| * \|	add identity layer	Qi Liu	2016-03-02
\| * \|	network init complete	Qi Liu	2016-03-01
\| * \|	add network & fix graph_layer	Qi Liu	2016-02-29
\| * \|	graph layer complete	Qi Liu	2016-02-29
\| \|/
* /	major change: clearer param binding semantics; permit rebinding; enable	Determinant	2016-03-10
\|/
*	clean up obsolete files	Determinant	2016-02-22
*	add layers from `layersT/` to `layer/`	Determinant	2016-02-21
*	generalize softmax_ce.lua (to softmax_ce_t.lua)	Determinant	2016-02-18
*	fixed some minor problem	txh18	2016-02-16
*	...	Determinant	2016-02-16
*	improve parameter auto-detection	Determinant	2016-02-16
*	move curand_gen out of the matrix layout	Determinant	2016-02-15
*	try a basic merge	Determinant	2016-02-15
*	changed affine_recurrent used in lm to affine_recurrent_plusvec	txh18	2015-12-23
*	trying to use lstm_t_v2 for ptb	txh18	2015-12-04
*	moved tnn to main nerv dir and added it to Makefile	txh18	2015-12-03
*	changed thres_mask function of matrix to a more standard api	txh18	2015-12-02
*	changed auto-generating params, won not save in global_conf.param	txh18	2015-11-25
*	let affine supported multiple inputs	txh18	2015-11-24
*	small bug fix	txh18	2015-11-23
\|\
\| *	correct the use of self.gconf	Determinant	2015-11-23
* \|	merge in recent changes about param updates	txh18	2015-11-23
\|\ \
\| * \|	small bug fix	txh18	2015-11-23
\| \|/
\| *	use consistent update calc; clean up code; no need for `direct_update`	Determinant	2015-11-21
* \|	added has_param api for param_repo	txh18	2015-11-20
* \|	complete auto-generate params	txh18	2015-11-20
* \|	working on automatic parameter for layers	txh18	2015-11-20
\|/
*	added atomicAdd for select_linear update, however, the result still seems unr...	txh18	2015-11-17
*	change updateEI to update_by_err_input	txh18	2015-11-16
*	coding style changes	txh18	2015-11-16
*	unified param updates, now direct_update is the same speed with undirect_update	txh18	2015-11-16
*	...	txh18	2015-11-16
*	used os.clock() for timer	txh18	2015-11-16
*	fixed direct update, did not know the result	txh18	2015-11-16
*	got good result when batch_size=1, strange!	txh18	2015-11-11
*	Merge pull request #6 from yimmon/master	Ted Yin	2015-10-12
\|\