“Chao Xing 2016-04-18”版本间的差异
来自cslt Wiki
第6行: | 第6行: | ||
3. Test for DNN-DSSM performance same to dongxu's experiments set. | 3. Test for DNN-DSSM performance same to dongxu's experiments set. | ||
− | * Get the results for test dataset : 60%, and train dataset : 77%[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=xingchao&step=view_request&cvssid=526 results] | + | * Get the results for test dataset : 60%, and train dataset : 77% [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=xingchao&step=view_request&cvssid=526 results] |
4. Code for mixture data version DNN-DSSM. | 4. Code for mixture data version DNN-DSSM. |
2016年4月18日 (一) 00:47的最后版本
Last Week:
1. Review DSSM work group's work during last four years.
2. Code done DSSM model including : DNN-DSSM, CNN-DSSM.
3. Test for DNN-DSSM performance same to dongxu's experiments set.
- Get the results for test dataset : 60%, and train dataset : 77% results
4. Code for mixture data version DNN-DSSM.
This Week:
1. Test for mixture-DNN-DSSM.
2. Code compare with :
- 1. DNN-DSSM target on cosine distance (same to their papers. Just consider positive sample).
- 2. DNN-DSSM target on negative sample max margin.
- 3. DNN-DSSM target on triplet max margin (consider both positive sample & negative sample).
- 4. Compare both DNN, CNN, RNN model target on different cost function above.
3. Test for 9 model above.