Difference between revisions of "2017-3-6"

From cslt Wiki
Jump to: navigation, search
(以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || || |- |Jiyuan Zhang || || |- |Andi Zhang || || |- |Shiyue...”为内容创建页面)
 
Line 12: Line 12:
 
|-
 
|-
 
|Andi Zhang ||
 
|Andi Zhang ||
 
+
* added source masks in attention_decoder where calculates attention and in gru_cell where calculates new states.
 +
* found the attribute sentence_length, perhaps it works better than my code
 
||
 
||
  
Line 18: Line 19:
 
|Shiyue Zhang ||  
 
|Shiyue Zhang ||  
 
* figured out the problem of attention: the initial value of V should be around 0
 
* figured out the problem of attention: the initial value of V should be around 0
* tested different modification, such as add mask, init b with 0. Compared the results, and concluded only change the initial value of V is the best.
+
* tested different modification, such as add mask, init b with 0.  
 +
* Compared the results, and concluded only change the initial value of V is the best.
 
||
 
||
 
* try to get right attention on memory
 
* try to get right attention on memory

Revision as of 03:03, 6 March 2017

Date People Last Week This Week
2017/1/3 Yang Feng
Jiyuan Zhang
Andi Zhang
  • added source masks in attention_decoder where calculates attention and in gru_cell where calculates new states.
  • found the attribute sentence_length, perhaps it works better than my code
Shiyue Zhang
  • figured out the problem of attention: the initial value of V should be around 0
  • tested different modification, such as add mask, init b with 0.
  • Compared the results, and concluded only change the initial value of V is the best.
  • try to get right attention on memory
Peilun Xiao