introduction to programming - jun jijun.hansung.ac.kr/ml/docs-slides-lecture8-kr.pdf ·...

신경망(Neural Networks): 표현

비선형모델

Machine Learning

Andrew Ng

비선형분류

x1

x2

size# bedrooms# floorsage

Andrew Ng

당신은이것을봅니다:

그러나카메라는이것을봅니다:

이것은무엇인가?

Andrew Ng

Computer Vision: 자동차감지

Testing:

What is this?

Not a carCars

Andrew Ng

Learning Algorithm

pixel 1

pixel 2

pixel 1

pixel 2

Raw image

Cars“Non”-Cars

Andrew Ng

pixel 1

pixel 2

Raw image

Cars“Non”-Cars

Learning Algorithm

pixel 1

pixel 2

Andrew Ng

pixel 1

pixel 2

Raw image

Cars“Non”-Cars

50 x 50 pixel images→ 2500 pixels(7500 if RGB)

pixel 1 intensity

pixel 2 intensity

pixel 2500 intensity

Quadratic features ( ): ≈3 millionfeatures

Learning Algorithm

pixel 1

pixel 2

Andrew Ng

신경망(Neural Networks): 표현

신경과뇌

Machine Learning

Andrew Ng

신경망(Neural Networks)

기원: 뇌를모방하기위한알고리즘.

80년대와 90년대초에절리사용되었음; 90년대후반에감소.

최근제기: 많은응용분야에서의첨단기술

Andrew Ng

청각피질이시각을학습한다.

청각피질(Auditory Cortex)

“학습알고리즘” 가설(hypothesis)

[Roe et al., 1992]

Andrew Ng

체성감각피질이시각을학습한다.

체성감각피질(Somatosensory Cortex)

The “one learning algorithm” hypothesis

[Metin & Frost, 1989]

Andrew Ng

혀로보기 사람반향위치측정 (음파탐지기:sonar)

촉각띠(Haptic belt): 방향감지 3번째눈심기

뇌에서의감각표현

[BrainPort; Welsh & Blasch, 1997; Nagel et al., 2005; Constantine-Paton & Law, 2009]

Neural Networks: Representation

Machine Learning

모델표현 I

Andrew Ng

뇌속의신경들

수상돌기

축색돌기

세포체

Andrew Ng

뇌속의신경들

[Credit: US National Institutes of Health, National Institute on Aging]

Andrew Ng

신경모델: 로지스틱(Logistic)단위

시그모이드(로지스틱) 활성함수

Sigmoid (logistic) activation function.

Andrew Ng

Neural Network

Layer 3Layer 1 Layer 2

Andrew Ng

Neural Network“activation” of unit in layer

matrix of weights controlling function mapping from layer to layer

If network has units in layer , units in layer , thenwill be of dimension .

Andrew Ng

Neural Networks: Representation

모델표현 II

Machine Learning

Andrew Ng

Add .

전방향전파: 백터화구현

Andrew Ng

Layer 3Layer 1 Layer 2

Neural Network learning its own features

Andrew Ng

Layer 3Layer 1 Layer 2

Other network architectures

Layer 4

Neural Networks: Representation

Examples and intuitions I

Machine Learning

Andrew Ng

비선형분류예 : XOR/XNOR

, 는이진수(binary) (0 or 1).

x1

x2

x1

x2

Andrew Ng

Simple example: AND

0 00 11 01 1

1.0

Andrew Ng

Example: OR function

0 00 11 01 1

-10

20

20

Neural Networks: Representation

Examples and intuitions II

Machine Learning

Andrew Ng

부정(Negation):

01

Andrew Ng

Andrew Ng

Putting it together:

0 00 11 01 1

-30

20

20

10

-20

-20

-10

20

20

Andrew Ng

Neural Network intuition

Layer 3Layer 1 Layer 2 Layer 4

Andrew Ng

Handwritten digit classification

[Courtesy of Yann LeCun]

Andrew Ng

Handwritten digit classification

[Courtesy of Yann LeCun]

Andrew Ng

Neural Networks: Representation

Multi-class classification

Machine Learning

Andrew Ng

Multiple output units: One-vs-all.

Pedestrian Car Motorcycle Truck

Want , , , etc.

when pedestrian when car when motorcycle

Andrew Ng

Multiple output units: One-vs-all.

Want , , , etc.

when pedestrian when car when motorcycle

Training set:

one of , , ,

pedestrian car motorcycle truck

Andrew Ng