質問

I understand boosting is a sequential learning technique and it use the prediction from previous model as a dataset for new model ,after adding weight to the misclassified data points. The point which was not clear how the weights are added for misclassified ones and diminished for the correctly classified ones. It would be great if veterans can help me to understand this

Thanks in advance

正しい解決策はありません

ライセンス: CC-BY-SA帰属
所属していません datascience.stackexchange
scroll top