Asr-language-processing-research-rnng-mn - 版本历史

Zhangsy：/* Time Table */

2016-11-21T06:55:15Z

‎Time Table

2016-11-14T08:05:42Z

‎Time Table

2016-11-08T00:55:50Z

‎Time Table

2016-11-07T10:55:24Z

‎Time Table

2016-11-07T04:46:35Z

‎Time Table

2016-11-07T04:43:46Z

‎Time Table

2016-11-07T04:42:33Z

‎Time Table

2016-11-07T04:30:17Z

‎Time Table

2016-11-07T03:26:47Z

‎Time Table

2016-11-02T09:03:10Z

‎Time Table

@@ 第58行： / 第58行： @@
 * refine the models tried before and give the result report
 * finish the code of dynamic memory model
-||  ||
+||
 |-
 | 2016/11/21
+|
-* modify model
+* try more different models
-* try to prove the positive function of dynamic memory
+# rerun original model, if the same result
 ||  ||
 |-

@@ 第40行： / 第40行： @@
 * how to use GPU in rnng
 # learn to use it
-||  ||
+||
 |-
 | 2016/11/14
+|
-* try to implement a dynamic memory
+* try to run rnng on multi cpu cores
 ||  ||
 |-

@@ 第37行： / 第37行： @@
 # modify model structure
 * read the code of Teacher Feng
-# understand
+# understand and run
 * how to use GPU in rnng
-# find how to use it
+# learn to use it
 ||  ||
 |-

@@ 第32行： / 第32行： @@
 | 2016/11/7
+|
-* modify model
+* modify discriminative model,  try to prove the positive function of static memory
-* try to prove the positive function of static memory
+# change train set
 ||  ||
 |-

@@ 第10行： / 第10行： @@
 | 2016/10/31
+|
-# implement rnng+static memory discriminative model
+* implement rnng+static memory discriminative model
-* fix the unexpected action
+# fix the unexpected action
-* rerun the original discriminative model
+#  rerun the original discriminative model
-* rerun the centred memory rnng model
+# rerun the centred memory rnng model
-* get wrong instances of original trained model, and get statistics
+#  get wrong instances of original trained model, and get statistics
-* run the wrong memory rnng model
+# run the wrong memory rnng model
-* run the sampled memory rnng model
+# run the sampled memory rnng model
-* update experiment report
+#  update experiment report
 ||
-* fixed the unexpected action
+* implementation is done, but result is not satisfied.
-* reran the original discriminative model
+#  fixed the unexpected action
-* reran the centred memory rnng model
+# reran the original discriminative model
-* got wrong instances of original trained model, and get statistics
+#  reran the centred memory rnng model
-* ran the sampled memory rnng model
+#  got wrong instances of original trained model, and get statistics
-* ran the wrong memory rnng model
+# ran the sampled memory rnng model
-* updated experiment report [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf]
+#  ran the wrong memory rnng model
 ||
 * 100%

@@ 第29行： / 第29行： @@
 |-
 | 2016/11/7
 | ||  ||
 |-
 | 2016/11/14
 | ||  ||
 |-
 | 2016/11/21
 | ||  ||
 |-
 | 2016/11/28
 | ||  ||
 |-
 | 2016/12/5
 | ||  ||
 |-
 | 2016/12/12
 | ||  ||
 |-
 | 2016/12/19
 | ||  ||
 |-
 | 2016/12/26
 | ||  ||
 |-
 |}
 ==Progress==

@@ 第7行： / 第7行： @@
 {| class="wikitable"
 !Date !! Work Plan !! Work Done !! Completion Rate
+|-
-| rowspan="6"|2016/10/31
+| 2016/10/31
 | ||  ||
 |-