Decision tree learning - Wikipedia
6
公开标注数
6
参与人数
2026-07-22 10:03:31
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-22 16:27:31
原文高亮摘录
“Bootstrap aggregated (or bagged) decision trees, an early ensemble method, builds multiple decision trees by repeatedly resampling training data with replacement, and voting the trees…”
Whisper 随想笔记
Bagging always felt like magic to me—just resample and vote, and it works way better.
划选高亮2026-07-22 13:24:31
原文高亮摘录
“Classification tree analysis is when the predicted outcome is the class (discrete) to which the data belongs.”
Whisper 随想笔记
But what if the data overlaps? Then it's not so clear-cut.
划选高亮2026-07-22 13:15:31
原文高亮摘录
“Classification tree analysis is when the predicted outcome is the class (discrete) to which the data belongs.”
Whisper 随想笔记
So it's like sorting things into boxes, got it.
划选高亮2026-07-22 10:21:31
原文高亮摘录
“Decision trees are among the most popular machine learning algorithms given their intelligibility and simplicity”
Whisper 随想笔记
They're cute for demos, but give me a linear model for real work.
划选高亮2026-07-22 10:12:31
原文高亮摘录
“Decision trees are among the most popular machine learning algorithms given their intelligibility and simplicity”
Whisper 随想笔记
Honestly I find random forests way more reliable in practice.
划选高亮2026-07-22 10:03:31
原文高亮摘录
“Decision trees are among the most popular machine learning algorithms given their intelligibility and simplicity”
Whisper 随想笔记
Yeah but they overfit like crazy without pruning, that's the catch.
分享本页 Whisper
短链接
https://domwhisper.com/s/1d915b5ede04嵌入代码
<iframe src="https://domwhisper.com/embed/1d915b5ede04" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>