Coursera machine learning week 6(二)
一 誤差分析 當應用機器學習時，建議的順序是： 1.首先構建一個比較簡單的模型或學習算法； 2.畫出模型的學習曲線、診斷模型是否有高偏差(欠擬合)或者高方差(過擬合)問題，從而決定是否需要更多的數據或者更多的特徵來解決； 3.誤差分析，手動檢查算法算錯的那些樣例，然後找出算法算錯的樣例術語那種類型。 二 偏斜類的誤差度量指標 2.1 偏斜類(Skewed classes)：是指假設一個樣本中有兩類
相關文章
- 1. Coursera Machine Learning Week 6 - Advice for Applying Machine Learning
- 2. Coursera machine learning week 6(一)
- 3. Sixth week of machine learning on Coursera
- 4. Third week of machine learning on Coursera
- 5. Seventh week of machine learning on Coursera
- 6. Second week of machine learning on Coursera
- 7. 【Machine Learning】【Andrew Ng】- Quiz(Week 6)
- 8. 機器學習系列之coursera week 6 Advice for Applying Machine Learning
- 9. 機器學習之Coursera Andrew Ng 《Machine Learning》 week 6 test 2
- 10. Machine Learning week 3
- 更多相關文章...
- • Docker Machine - Docker教程
- • Hibernate的二級緩存 - Hibernate教程
- • RxJava操作符（二）Transforming Observables
- • Kotlin學習（二）基本類型
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Coursera Machine Learning Week 6 - Advice for Applying Machine Learning
- 2. Coursera machine learning week 6(一)
- 3. Sixth week of machine learning on Coursera
- 4. Third week of machine learning on Coursera
- 5. Seventh week of machine learning on Coursera
- 6. Second week of machine learning on Coursera
- 7. 【Machine Learning】【Andrew Ng】- Quiz(Week 6)
- 8. 機器學習系列之coursera week 6 Advice for Applying Machine Learning
- 9. 機器學習之Coursera Andrew Ng 《Machine Learning》 week 6 test 2
- 10. Machine Learning week 3