data_mining:error_analysis

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
data_mining:error_analysis [2018/05/21 22:11]
phreazer [Problems with different train and dev/test set dist]
data_mining:error_analysis [2018/05/21 22:24] (current)
phreazer [Problems with different train and dev/test set dist]
Line 184: Line 184:
     * Degree of overfitting to dev set (if to high => bigger dev set)     * Degree of overfitting to dev set (if to high => bigger dev set)
   * Test: 12%   * Test: 12%
 +
 +====== Data mismatch problems ======
 +
 +  * Error analysis to understand difference between training and dev/test set
 +  * Make training more similar / collect more data similar to dev/test set (e.g. simulate audio environment)
 +    * Artificial data synthesis
 +      * Problems: Possible that sampling from too few data (for human it might appear ok)
  • data_mining/error_analysis.txt
  • Last modified: 2018/05/21 22:24
  • by phreazer