20
Logo the feasibility of machine learning

the feasibility of machine learning

  • Upload
    ula

  • View
    76

  • Download
    0

Embed Size (px)

DESCRIPTION

the feasibility of machine learning . Component of learning. Formalization Input (输入) :X (customer application) think of it as deed dimension vector Output (输出) :Y(+1,-1) good/bad customer Target Function( 目标函数 ) : f :x → y ideal credit approval formula. Component of learning. - PowerPoint PPT Presentation

Citation preview

Page 1: the feasibility of machine learning

Logo

the feasibility of machine learning

Page 2: the feasibility of machine learning

Logo

Company Logo

Component of learning

Formalization – Input (输入) :X (customer application) think of it as deed dimension vector

– Output (输出) :Y(+1,-1) good/bad customer

– Target Function( 目标函数 ) : f :x→y ideal credit approval formula

Page 3: the feasibility of machine learning

Logo

Company Logo

Component of learning

Formalization – Data (数据) : (), (),…, () historical records

↓ ↓ ↓– Hypothesis( 假设 ) : g :x→y为了得到目标函数的公式

F is unknown G is very much knownactually we created it

Page 4: the feasibility of machine learning

Logo

Company Logo

Component of learning

UNKNOWN TARGET FUNCTION f :x→y ↓ ↓

TRAINING EXAMPLES (), (),…, ()

FINAL HYPOTHESIS g

(G hopefully approximates F)

Page 5: the feasibility of machine learning

Logo

Company Logo

Component of learning

UNKNOWN TARGET FUNCTION f :x→y ↓ ↓

TRAINING EXAMPLES (), (),…, ()

FINAL HYPOTHESIS g

(G hopefully approximates F)

Page 6: the feasibility of machine learning

Logo

Company Logo

Component of learning

TRAINING EXAMPLES (), (),…, ()

LEARNING ALGORITHM →HYPOTHESIS SET( 从现实模型公式中创造公式) (将它们成为假设集)

FINAL HYPOTHESIS

Page 7: the feasibility of machine learning

Logo

Company Logo

Component of learning

HYPOTHESIS SET H

从假设集选出一个假设H 衍生出一堆 H’s( 待定函数 )

Page 8: the feasibility of machine learning

Logo

Company Logo

Component of learning

UNKNOWN TARGET FUNCTION f :x→y ↓ ↓

TRAINING EXAMPLES (), (),…, ()

FINAL HYPOTHESIS g

(G hopefully approximates F)

Page 9: the feasibility of machine learning

Logo

Company Logo

HYPOTHESIS SET

Hypothesis Set – H = {h} g∈ H

Learning Algorithm– Together. they are referred to as the

learning model. a hypothesis set and a learning algorithm

Page 10: the feasibility of machine learning

Logo

Company Logo

A simple hypothesis set—’perceptron’

For input X= attributes of a customer– Approve credit if

> threshold

– Deny credit if < threshold

This linear formula h∈ H can be written ash(x) = sign( () – threshold )

Page 11: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Page 12: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

A related experiment

P(picking red)=μ P(picking green)=1-μ

μ=probability of red marbles

Page 13: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Pick N marbles independently

The fraction of red marbles in sample = v

Page 14: the feasibility of machine learning

Logo

Company Logo

Does v Say anything about μ?

NO!

Sample can be mostly green while bin is mostly red

Page 15: the feasibility of machine learning

Logo

Company Logo

Does v Say anything about μ?

Yes

Sample frequency v is close to bin frequency μ

This is called Hoeffding Inequality

Page 16: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Bin – Unknown is a number μ

Learning – Unknown is a function f:x→y

each marble is a point x ∈ X

Page 17: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Bin – Unknown is a number μ

Learning – Unknown is a function f:x→y

each marble is a point x ∈ X

Hypothesis got it right h(x)=f(x)

Page 18: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Bin – Unknown is a number μ

Learning – Unknown is a function f:x→y

each marble is a point x ∈ X

Hypothesis got it wrong h(x)≠f(x)

Page 19: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

UNKNOWN TARGET FUNCTION f :x→y ↓ ↓

TRAINING EXAMPLES (), (),…, ()

FINAL HYPOTHESIS g

(G hopefully approximates F)

Page 20: the feasibility of machine learning

Logo

Company Logo

Learning Feasible

Probability distribution

P on X