17. Addressing Data Mismatch
2023. 9. 15. 00:18ㆍGoogle ML Bootcamp/3. Structuring Machine Learning Projects
1. try to understand difference between training and dev/test sets
2. make training data more similar or collect more data similar to dev/test sets.
- 녹음된 목소리 + 차 소음 = 합성된 데이터 similar to real data(dev, test sets)
따라서 Data Mismatch를 해결할 방법은 인공 데이터 합성. make training data more similar to dev/test sets.
'Google ML Bootcamp > 3. Structuring Machine Learning Projects' 카테고리의 다른 글
| 19. Multi-task Learning (0) | 2023.09.15 |
|---|---|
| 18. Transfer Learning (0) | 2023.09.15 |
| 16. Bias and Variance with Mismatched Data Distributions (0) | 2023.09.15 |
| 15. Training and Testing on Different Distributions (0) | 2023.09.14 |
| 14. Bulid your First System Quickly, then Iterate (0) | 2023.09.14 |