机器学习-黄迪2 线性回归

VIP免费

2025-01-13 0 0 4.07MB 86 页 5.9玖币

侵权投诉

机器学习

Machine Learning

北京航空航天大学计算机学院

School of Computer Science and Engineering, Beihang University

黄迪刘庆杰

2018年秋季学期

Fall 2018

部分内容来源于C. Bishop和A. NG等人的课程以及互联网资源

第一章：机器学习概述(续)

Chapter 1: Introduction to Machine Learning

训练和测试

训练集

(观测)

通用数据集

(非观测)

测试集

(非观测)

数据获取实际运用

Training is the process of making the system able to learn.

No free lunch rule:

–Training set and testing set come from the same distribution

–Need to make some assumptions or bias

训练和测试

There are several factors affecting the performance:

–Types of training provided

–The form and extent of any initial background knowledge

–The type of feedback provided

–The learning algorithms used

Two important factors:

–Modeling

–Optimization

评价标准

Supervised: Low E-out or maximize probabilistic terms

Unsupervised: Minimum quantization error, Minimum

distance, MAP, MLE (Maximum Likelihood Estimation)

机器学习目标

E-in: for training set

E-out: for testing set

Under-fitting VS. Over-fitting (fixed N)

机器学习目标

error

(model = hypothesis + loss

functions)

机器学习目标

Components of generalization error

Bias: how much the average model over all training

sets differ from the true model?

–Error due to inaccurate assumptions/simplifications made

by the model

Variance: how many models estimated from different

training sets differ from each other

机器学习目标

Under-fitting: model is too “simple” to represent all the

relevant class characteristics

–High bias and low variance

–High training error and high test error

Over-fitting: model is too “complex” and fits irrelevant

characteristics (noise) in the data

–Low bias and high variance

–Low training error and high test error

机器学习目标

Models with too few parameters

are inaccurate because of a large

bias (not enough flexibility).

Models with too many parameters

are inaccurate because of a large

variance (too much sensitivity to

the sample).

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

5.9 玖币 0人已下载

立即下载 VIP免费下载

摘要：

机器学习MachineLearning北京航空航天大学计算机学院SchoolofComputerScienceandEngineering,BeihangUniversity黄迪刘庆杰2018年秋季学期Fall2018部分内容来源于C.Bishop和A.NG等人的课程以及互联网资源第一章：机器学习概述(续)Chapter1:IntroductiontoMachineLearning训练和测试训练集(观测)通用数据集(非观测)测试集(非观测)数据获取实际运用Trainingistheprocessofmakingthesystemabletolearn.Nofreelunchrule:–Tr...

展开>> 收起<<

机器学习-黄迪2 线性回归.pdf

共86页,预览18页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

机器学习-黄迪2 线性回归

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: