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

	Commit message (Collapse)	Author	Age
*	small bug fix in lm training script	txh18	2015-12-06
\|
*	small bug fix in lm training script	txh18	2015-12-05
\|
*	added twitter, added bilstmlm script, todo: test bilstmlm	txh18	2015-12-05
\|
*	changed lstm_t to a more standard version	txh18	2015-12-05
\|
*	small bug fix for lmptb.lstm_t_v2	txh18	2015-12-04
\|
*	trying to use lstm_t_v2 for ptb	txh18	2015-12-04
\|
*	added one_sen_report to lm_process_file	txh18	2015-12-04
\|
*	...	txh18	2015-12-04
\|
*	added testout command for lstmlm	txh18	2015-12-04
\|
*	added log_redirect to SUtil	txh18	2015-12-04
\|
*	applying dropout on lstm.h before combinerL seems bad, PPL only 95, trying ↵	txh18	2015-12-03
\| \| \| \|	another way(like in the paper) of dropout for lstm.h after combinerL
*	added two layers to lstmlm_ptb, todo:test it	txh18	2015-12-03
\|
*	added al_sen_start stat for lmseqreader	txh18	2015-12-03
\|
*	moved tnn to main nerv dir and added it to Makefile	txh18	2015-12-03
\|
*	...	txh18	2015-12-03
\|
*	small bug fix in tnn for se_mode, todo:test it	txh18	2015-12-02
\|
*	added se_mode for lmseqreader, todo:check it	txh18	2015-12-02
\|
*	function name change in LMTrainer	txh18	2015-12-02
\|
*	added dropout_t layer	txh18	2015-12-02
\|
*	changed thres_mask function of matrix to a more standard api	txh18	2015-12-02
\|
*	added rand_uniform and thres_mask for cumatrix	txh18	2015-12-01
\|
*	got PPL115 for ptb on h300lr1bat10wc1e-4	txh18	2015-12-01
\|
*	bug fix for lstm_t layer, t not inclueded in propagate!	txh18	2015-11-30
\|
*	small opt for initing tnn:clip_t	txh18	2015-11-30
\|
*	added ooutputGate for lstm_t	txh18	2015-11-30
\|
*	bug fix: tanh implementation could cause nan	txh18	2015-11-29
\|
*	added clip_t for tnn	txh18	2015-11-27
\|
*	lstm_tnn can be run, todo:testing	txh18	2015-11-27
\|
*	still working..	txh18	2015-11-26
\|
*	working on lstm	txh18	2015-11-26
\|
*	changed auto-generating params, won not save in global_conf.param	txh18	2015-11-25
\|
*	added tanh operation for matrix	txh18	2015-11-25
\|
*	let affine supported multiple inputs	txh18	2015-11-24
\|
*	added wcost for biasparam in lm_trainer	txh18	2015-11-24
\|
*	still working on dagL_T	txh18	2015-11-24
\|
*	completed layerdag_t, now testing...	txh18	2015-11-23
\|
*	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
\|\ \ \| \| \| \| \| \| \| \| \|	Merge branch 'master' into txh18/rnnlm
\| * \|	small bug fix	txh18	2015-11-23
\| \|/
\| *	add cflag __NERV_FUTURE_CUDA_7	Determinant	2015-11-23
\| \|
\| *	use consistent update calc; clean up code; no need for `direct_update`	Determinant	2015-11-21
\| \|
* \|	completed gate_fff layer	txh18	2015-11-23
\| \|
* \|	implementing GateFFF layer	txh18	2015-11-23
\| \|
* \|	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
\| \|
* \|	changed work_dir setting	txh18	2015-11-18
\|/
*	small coding style change	txh18	2015-11-18
\|
*	h300 and h400 worked well, log added	txh18	2015-11-18
\|