10机器学习_课程教案

Machine Learning Course Plan

Lecture One

Title:

Introduction

Content:

?

Basic information about this course: books, TA, office, homework, project

and test form

…

?

Introduce the definition of learning systems.

?

Give an overview of applications to show the goals of machine learning.

?

Introduce the aspects of developing a learning system: training data, concept

representation, function approximation.

Targets:

?

Understand the background of machine learning;

?

Remember the basic function of machine learning;

?

Get the general ideas of machine learning

’

s problem and point;

Processions:

?

What is Machine Learning?

?

Applications of ML

?

Disciplines relevant to ML

?

Well-Posed Learning Problems

?

Designing a Learning System

?

Perspectives and Issues In Machine Learning

?

How To Read This Book

Difficulties:

?

How to design a learning system;

?

The understand of concept.

Lecture Two

Title:

Concept Learning and the General-to- Specific Ordering

Contents:

?

What is the concept learning task? Where is it applied to?

?

Make students understand concept learning is equivalent to search through a

hypothesis space.

?

Illustrate

step

by

step

the

procedure

of

general-to-specific

ordering

of

hypotheses, to find the maximally specific hypotheses

Targets:

?

Understand the background of concept learning;

?

Remember the basic concept of concept learning, version space, etc;

Processions:

?

Introduction

?

A Concept Learning Task

?

Concept Learning as Search

?

Find-S

：

Finding a Maximally Specific Hypothesis

Difficulties:

?

What

’

s the process of concept learning;

?

Remember the concept of concept learning;

Lecture Three

Title:

Candidate elimination and Inductive bias

Contents:

?

Introduce

the

definition

of

version

spaces

and

the

candidate

elimination

algorithm.

?

How to learning conjunctive concepts?

?

Introduce and emphasize the importance of inductive bias.

Targets:

?

Remember the process of candidate elimination algorithm;

?

Get the basic idea of the useless of unbiased learning;

Processions:

?

Version Spaces and the Candidate- Elimination Algorithm

?

Remarks On VS and C-E

?

Inductive Bias

Difficulties:

?

The understand of version space;

?

The idea of bias;

?

The under stand of Find-S Algorithm and Candidate- Elimination Algorithm;

Assignments:

?

EX. 2.1

?

EX. 2.4

Lectrue Four

Title:

Decision Tree Learning(1)

Contents:

?

Development

of

Decision

tree

learning,

the

role

it

plays

in

the

history

of

increcemental learning

?

Show the students how to representing concepts as decision trees.

?

Introduce recursive induction of decision trees.

Targets:

?

Understand the background of Decision Tree;

?

Remember the basic concept of decision tree, over fitting, etc;

Processions:

?

Introduction

?

Decision Tree Representation

?

Appropriate Problems for Decision Tree Learning

Difficulties:

?

One of the most widely used and practical methods for inductive inference

?

A method for approximating discrete-valued functions

?

Robust to noisy data

?

Capable of learning disjunctive expressions

Lectrue Five

Title:

Decision Tree Learning(2)

Contents:

?

Introduce recursive induction of decision trees.

?

Picking the best splitting attribute: entropy and information gain. Emphasize

this part, let students do exercise to practice the procedure

Targets:

?

Remember the process of the learning algorithm of decision tree;

Processions:

?

The Basic Decision Tree Learning Algorithm

?

Hypothesis Space Search ID3

Difficulties:

?

ID3, Assistant, C4.5

Lectrue Six

Title:

Decision Tree Learning(3)

Contents:

?

What

is

Overfitting?

When

will

is

happen?

What

damage

will

it

cause

to

classifiers?

What

should

be

done

in

case

of

noisy

data?

Why

and

how

to

prune?

?

How to apply the decision tree to continuous attributes and missing values.

Targets:

?

Get the basic idea of solving the problems;

Processions:

?

Inductive Bias in Decision Tree Learning

?

Issue In Decision Tree Learning

Difficulties:

?

Inductive bias is a preference for small trees over large trees

?

Can also be re- presented as sets of if-then rules

Lectrue Seven

Title:

Artificial Neural Networks(1)