“Dongxu Zhang 2015-09-14”版本间的差异
来自cslt Wiki
（以“Last Week: 1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test s...”为内容创建页面） |
|||
| （相同用户的一个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
Last Week: | Last Week: | ||
| − | 1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). | + | 1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test set gets best result when training error is around 0.98. |
| − | + | ||
| − | + | ||
2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1) | 2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1) | ||
2015年9月15日 (二) 07:39的最后版本
Last Week:
1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test set gets best result when training error is around 0.98.
2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1)
3. Tried a simple idea on Graph prediction.
This Week:
1. Tried features for softmax. And tried smaller lambda.
2. tune the performance of transE. and check out if the idea works.
3. Try sequence supervised learning. Compare with Viterbi.
