Upgrade to Pro — share decks privately, control downloads, hide ads and more …

了解KNN算法

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →
Avatar for yafei002 yafei002
January 08, 2017
Technology
0
170

 了解KNN算法

Avatar for yafei002

yafei002

January 08, 2017
Tweet

More Decks by yafei002

See All by yafei002
了解人工神经网络
Avatar for yafei002 yafei002
1
220
了解朴素贝叶斯
Avatar for yafei002 yafei002
1
230
了解K-Means算法
Avatar for yafei002 yafei002
1
210
了解决策树和C4.5算法
Avatar for yafei002 yafei002
1
270
数据可视化之视觉感知与认知
Avatar for yafei002 yafei002
1
390
数据可视化之地理信息可视化
Avatar for yafei002 yafei002
1
400
数据可视化之层次和网络数据可视化（上）
Avatar for yafei002 yafei002
1
680
数据可视化之复杂高维多元数据的可视化（上）
Avatar for yafei002 yafei002
1
290
Data Visualization Introduction and History
Avatar for yafei002 yafei002
1
320

Other Decks in Technology

See All in Technology
不確実性と戦いながら見積もりを作成するプロセス/mitsumori-process
Avatar for hiro@miraito hirodragon112
1
140
Why we keep our community?
Avatar for Yasunobu Kawaguchi kawaguti
PRO
0
350
会社紹介資料 / Sansan Company Profile
Avatar for Sansan, Inc. sansan33
PRO
16
410k
ADK + Gemini Enterprise で 外部 API 連携エージェント作るなら OAuth の仕組みを理解しておこう
Avatar for Kaz kaz1437
0
240
Cursor Subagentsはいいぞ
Avatar for Yuji Yamaguchi yug1224
2
120
AIエージェント勉強会第3回 エージェンティックAIの時代がやってきた
Avatar for Y.Miyado ymiya55
0
170
OCI技術資料 : ロード・バランサ 概要 - FLB・NLB共通
Avatar for Oracle Cloud Infrastructure ソリューション・エンジニア ocise
4
27k
「できない」のアウトプット 同人誌『精神を壊してからの』シリーズ出版を 通して得られたこと
Avatar for comi comi190327
3
110
やさしいとこから始めるGitHubリポジトリのセキュリティ
Avatar for Yuta Matsumura tsubakimoto_s
3
2.1k
OPENLOGI Company Profile for engineer
Avatar for OPENLOGI hr01
1
61k
Databricks Appsで実現する社内向けAIアプリ開発の効率化
Avatar for R-Miura r_miura
0
150
SaaSの操作主体は人間からAIへ - 経理AIエージェントが目指す深い自動化
Avatar for Motoshi Nishihira nishihira
0
120

Featured

See All Featured
Writing Fast Ruby
Avatar for Erik Berlin sferik
630
63k
The Limits of Empathy - UXLibs8
Avatar for Cassini Nazir cassininazir
1
280
More Than Pixels: Becoming A User Experience Designer
Avatar for Michelle Schulp Hunt marktimemedia
3
360
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
Avatar for Sophie Logan marketingsoph
0
120
Tips & Tricks on How to Get Your First Job In Tech
Avatar for Honza Javorek honzajavorek
0
470
Music & Morning Musume
Avatar for Bryan Veloso bryan
47
7.1k
Leveraging Curiosity to Care for An Aging Population
Avatar for Cassini Nazir cassininazir
1
200
Done Done
Avatar for chrislema chrislema
186
16k
Building Adaptive Systems
Avatar for Chris Keathley keathley
44
3k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
Avatar for Mfonobong Umondia mfonobong
2
340
Abbi's Birthday
Avatar for Violet Bock coloredviolet
2
6k
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
57
14k

Transcript

  1. 了解KNN算法 yafei002

  2. a a a a a a a a o o

    o c o o o 给定N个训练样本， 无论什么类别，KNN算法识别离目标最近的k个邻居

  3. a 当k=1时，在空间中每个样本确定一个区域，也就是Voronoi分区 e c b R1 R2 R3 R4

  4. 注意 • 对于二分类问题k选择为奇数 • k不能是类别数量的整数倍 • KNN算法的主要缺点是复杂度，它需要搜索所有的样本从而找到最近的邻居

  5. THANKS