SlideShare une entreprise Scribd logo
1  sur  58
Télécharger pour lire hors ligne
© 2020, Amazon Web Services, Inc. or its Affiliates.
Sungmin, Kim
AWS Solutions Architect
1시간 만에 머신 러닝
개념 따라잡기
© 2020, Amazon Web Services, Inc. or its Affiliates.
Agenda
• Machine Learning 이란?
• Machine Learning으로 풀 수 있는 문제 유형
• Machine Learning 작업 순서
• ML 학습을 위한 입력 데이터 가공하기 - Feature Engineering
• ML과 최적화 문제 - Loss Function & Gradient Decent method (경사하강법)
• ML 학습 속도와 모델 성능 향상을 위한 Hyper Parameter Tuning
• 미래를 위한 준비 - 데이터 나누기 (Train/Validation/Test)
• ML 모델 선택 시 주의할 점 - Overfitting vs. Underfitting
• 여러 가지 ML 모델 결합 하기 - Ensemble method
• Deep Learning
© 2020, Amazon Web Services, Inc. or its Affiliates.
Marketing Offer On A New Product
© 2020, Amazon Web Services, Inc. or its Affiliates.
Option 1- Build A Rule Engine
Age Gender Purchase
Date
Items
30 M 3/1/2017 Toy
40 M 1/3/2017 Books
…. …… ….. …..
Input Output
Age Gender Purchase
Date
Items
30 M 3/1/2017 Toy
…. …… ….. …..
Rule 1: 15 <age< 30
Rule 2: Bought Toy=Y,
Last Purchase<30 days
Rule 3: Gender = ‘M’,
Bought Toy =‘Y’
Rule 4: ……..
Rule 5: ……..
Human
Programmer
© 2020, Amazon Web Services, Inc. or its Affiliates.
Model
Output
Historical Purchase Data
(Training Data)
Prediction
Age Gender Items
35 F
39 M Toy
Input - New Unseen Data
Age Gender Purchase
Date
Items
30 M 3/1/2017 Toy
40 M 1/3/2017 Books
…. …… ….. …..
Learning
Algorithm
Option 2 - Learn The Business Rules From Data
© 2020, Amazon Web Services, Inc. or its Affiliates.
We Call This Approach Machine Learning
Model
Output
Historical Purchase Data
(Training Data)
Prediction
Age Gender Items
35 F
39 M Toy
Input - New Unseen Data
Age Gender Purchase
Date
Items
30 M 3/1/2017 Toy
40 M 1/3/2017 Books
…. …… ….. …..
Rule 1: 15 <age< 30
Rule 2: Bought Toy=Y,
Last Purchase<30
days
Rule 3: Gender = ‘M’,
Bought Toy =‘Y’
Rule 4: ……..
Rule 5: ……..
Human
Programmer
Learning
Algorithm
© 2020, Amazon Web Services, Inc. or its Affiliates.
Classical
Programming
Machine
Learning
Data
Rules
Data
Answers
Answers
Rules
Machine Learning: Paradigm Shift
© 2020, Amazon Web Services, Inc. or its Affiliates.
What is Learning Algorithm?
Input X (size of house)
Output Y
(price)
f(x) = W*x + b
xo
xn
2
3
1
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning Algorithm
f(x) = W*x + b
• W = ?
• b = ?
모델
학습
대상
Size (X)
2104
1600
2400
1416
3000
1985
1534
1427
1380
1494
Price (y)
400
330
369
232
540
300
315
199
212
243
✗
✗
✗
✗
✗
✗
✗
✗
Input X (size of house)
Output Y
(Price)
2
3
1
(1), (2), (3) 중 가장 적합한(fit) 것은?
Dataset
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning Algorithm
f(x) = W*x + b
• W = ?
• b = ?
모델
학습
대상
Size (X)
2104
1600
2400
1416
3000
1985
1534
1427
1380
1494
Price (y)
400
330
369
232
540
300
315
199
212
243
(1), (2), (3) 중 가장 적합한(fit) 것은?
Dataset
• 입력 데이터는 모두 숫자이다.
• ML의 모델은 수학적 모형(수식) 이다.
• ML의 결과물은 수식의 매개변수 이다.
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning Algorithm
Input
Data Model
Program
ML
Algorithm
숫자
0, 1, 2,..
0.01, 0.02,..
001, 010, 011, ..
model
{w1, w2, …, wn, b}
f(x) = w1*x1 + w2*x2 + … + wn*xn + b
= W*x + b
ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법
Output
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning으로 풀 수 있는 문제 유형
Supervised
Unsupervised
정답?
Prediction
Classification
Clustering
Reinforcement
• Linear Regression
• Logistic Regression
• SVM
• K-NN
• XGBoost
• K-Means
• DBScan
Density
Estimation
• PCA
• t-SNE
Yes
No
• Monte Carlo
• Q-Learning
• DQN
© 2020, Amazon Web Services, Inc. or its Affiliates.
Supervised Learning
It is a cat.
No, it’s a
Labrador.
• The algorithm is given a set of training examples
where the data and target are known. It can then
predict the target value for new datasets,
containing the same attributes
• Human intervention and validation required
Example: Photo classification and tagging
© 2020, Amazon Web Services, Inc. or its Affiliates.
Supervised Learning – How Machines Learn
Human intervention and validation required
e.g. Photo classification and tagging
Input
Label
Machine
Learning
Algorithm
Labrador
Prediction
Cat
Training Data
?
Label
Labrador
Adjust Model
© 2020, Amazon Web Services, Inc. or its Affiliates.
Unsupervised Learning
Input
Machine
Learning
Algorithm
Prediction
• Algorithm is given mass amounts of data, and it must find
patterns and relationships between the data. It can then draw
inferences from datasets
• Human intervention is not required
Example: Auto-classification of documents based on context
© 2020, Amazon Web Services, Inc. or its Affiliates.
Reinforcement Learning
Action
Environment
State Rewards
Agent
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning Use Cases
Supervised Learning
Ø Classification
• Spam detection
• Customer churn
prediction
Ø Regression
• House price prediction
• Demand forecasting
Unsupervised Learning
Ø Clustering
• Customer segmentation
Reinforcement Learning
Ø Self Driving Car
Ø Robots
© 2020, Amazon Web Services, Inc. or its Affiliates.
기계 학습 유형
Supervised
Unsupervised
정답?
Prediction
Classification
Clustering
Reinforcement
• Linear Regression
• Logistic Regression
• SVM
• K-NN
• XGBoost
• K-Means
• DBScan
Density
Estimation
• PCA
• t-SNE
Yes
No
• Monte Carlo
• Q-Learning
• DQN
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning Workflow
현실 문제를 Machine Learning을 이용해서 어떻게 풀 수 있을까?
ML
Problem
Framing
Raw Data
Real-World
Problem
Define ML
Problem
Data
Preparation
Build Training Deploy
© 2020, Amazon Web Services, Inc. or its Affiliates.
ML Problem Framing
현실
문제
ML
문제
집 값 예측
(1) 어떤 ML 문제 유형인지 파악
• 예측
• 분류
• 군집화
• ….
입력 (X)
• 방 개수
• 방 크기
• 위치
• 준공 연도
• 주변 시설
• …
집 값 (y)
(2) 입력/출력 설계
✓
Prediction
(Supervised Learning)
© 2020, Amazon Web Services, Inc. or its Affiliates.
ML 문제 분류
Predict or
forecast a
value?
Unsupervised
Learning
Supervised
Learning
Classification Regression Clustering
Density
estimation
Yes No
Discrete
target value
Continuous
target value
Fit data into
discrete groups
Numeric
estimate to fit
https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning: Input 설계
Data Model
ML
Algorithm
숫자
0, 1, 2,..
0.01, 0.02,..
001, 010, 011, ..
model
{w1, w2, …, wn, b}
f(x) = w1*x1 + w2*x2 + … + wn*xn + b
= W*x + b
ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법
© 2020, Amazon Web Services, Inc. or its Affiliates.
모든 입력 데이터는 숫자(Number)
손 글씨 이미지 숫자
© 2020, Amazon Web Services, Inc. or its Affiliates.
모든 입력 데이터는 숫자(Number)
문자열 또는 카테고리 데이터는 One-Hot Encoding 방식을 이용해서 숫자로 변환
상품 분류 가격
TV 1,000,000
냉장고 1,500,000
전자렌지 200,000
컴퓨터 800,000
선풍기 100,000
선풍기 100,000
믹서 50,000
믹서 50,000
상품 분류 가격
0 1,000,000
1 1,500,000
4 200,000
5 800,000
3 100,000
3 100,000
2 50,000
2 50,000
TV 냉장고 믹서 선풍기 전자렌지 컴퓨터 가격
1 0 0 0 0 0 1,000,000
0 1 0 0 0 0 1,500,000
0 0 0 0 1 0 200,000
0 0 0 0 0 1 800,000
0 0 0 1 0 0 100,000
0 0 0 1 0 0 100,000
0 0 1 0 0 0 50,000
0 0 1 0 0 0 50,000
원본 데이터 숫자 인코딩 One-Hot 인코딩
© 2020, Amazon Web Services, Inc. or its Affiliates.
Feature: 숫자로 변환된 ML 알고리즘의 입력 데이터
© 2020, Amazon Web Services, Inc. or its Affiliates.
Feature Engineering
• 입력 데이터를 숫자로 변환하기
ex) One-Hot Encoding
• 데이터의 가지 수 (차원)를 줄이거나
늘리는 작업
• 불필요한 데이터를 제거하기
• 누락된 데이터를 채워 넣기
• …
1차원
2차원
6 차원
Feature
© 2020, Amazon Web Services, Inc. or its Affiliates.
차원의 저주 (Curse of Dimensionality)
…
…
1차원 2차원 3 차원 4 차원
…
…
…
…
13 차원 784 차원 54877 차원
Iris MNIST Farm Ads
꽃받침 길이,
꽃받침 너비,
꽃잎 길이,
꽃잎 너비
pixel1,
pixel2,
…,
pixel784
단어1,
단어2,
…,
단어54877
© 2020, Amazon Web Services, Inc. or its Affiliates.
모델 평가
Data Model
ML
Algorithm
숫자
0, 1, 2,..
0.01, 0.02,..
001, 010, 011, ..
model
{w1, w2, …, wn, b}
f(x) = w1*x1 + w2*x2 + … + wn*xn + b
= W*x + b
ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법
✗
✗
✗
✗
✗
✗
✗
✗
Input X (size of house)
Output Y
(Price)
2
3
1
Q) (1), (2), (3) 중 가장 적합한(fit) 것은?
© 2020, Amazon Web Services, Inc. or its Affiliates.
Input X (size of house)
Loss Function (Objective Function)
Output Y
(Price)
f(x) = W*x + b
Error (f(Xj) – Yj)
Loss(W, b) = ∑(f(xj) – yj)2
1
n j=1
n
xo
xn
Mean Square Error(MSE) Function
Guessing
Value
Actual
Value
© 2020, Amazon Web Services, Inc. or its Affiliates.
Loss Function (Objective Function)
선형 회귀 문제
선형 회귀를 위한 목적 함수
• 𝑓!(𝐱")는 예측함수의 출력, yi는 예측함수가
맞추어야 하는 목표 값
• 𝑓!(𝐱") - yi는 오차 = 평균제곱오차MSE(mean squared error)
© 2020, Amazon Web Services, Inc. or its Affiliates.
Loss Function (Objective Function)
선형 회귀 문제
선형 회귀를 위한 목적 함수
• 𝑓!(𝐱")는 예측함수의 출력, yi는 예측함수가
맞추어야 하는 목표 값
• 𝑓!(𝐱") - yi는 오차 = 평균제곱오차MSE(mean squared error)
처음에는 최적 매개변수 값을 알 수 없으므로 임의
값으로 Θ! = 𝑤!, 𝑏! 설정 à Θ" = 𝑤", 𝑏" 로
개선 à Θ# = 𝑤#, 𝑏# 로 개선 à Θ#는 최적해 &
Θ
• 이때 𝐽 Θ# > 𝐽 Θ$ > 𝐽 Θ%
© 2020, Amazon Web Services, Inc. or its Affiliates.
Plotting Loss Function (Single Variable)
W
Loss (W)
Minimum loss
© 2020, Amazon Web Services, Inc. or its Affiliates.
Optimization - Minimize Loss Function
W
Minimum loss
현 지점의
기울기
(Partial
Derivative)
Loss를 낮추는
방향(Descent)
WJ WJ+1
Gradient Descent
Wj+1 = Wj 𝛼 Loss(Wj)
∂
∂Wj
Random
initial value
Loss (W)
𝛼
한 발자국 크기
(Learning Rate)
© 2020, Amazon Web Services, Inc. or its Affiliates.
Gradient Decent: 최적화 문제 해결법
Learning Step
weight의 업데이트 = 에러 낮추는 방향 x 한 발자국 크기 x 현 지점의 기울기
(decent) (learning rate) (gradient)
Loss function의 현재 가중치에서 기울기(gradient)를 구해서 Loss를 줄이는 방향으로 가중치를 업데이트해
나간다
Learning Rate
© 2020, Amazon Web Services, Inc. or its Affiliates.
Hyper Parameter
Learning Rate(학습률)는 어떻게 설정해야할까?
Data Model
ML
Algorithm
숫자
0, 1, 2,..
0.01, 0.02,..
001, 010, 011, ..
model
{w1, w2, …, wn, b}
f(x) = w1*x1 + w2*x2 + … + wn*xn + b
= W*x + b
Gradient Descent
알고 싶은 값
(Parameter)
모델 학습을 위해서 미리
알아야 하는 값
(Hyperparameter)
© 2020, Amazon Web Services, Inc. or its Affiliates.
small learning rate right learning rate large learning rate
Hyper Parameter Tuning (HPO)
(학습이) 너무 느리다 답을 찾지 못한다
© 2020, Amazon Web Services, Inc. or its Affiliates.
Weight 초기값, Learning Rate 등을 적절하게 선택해야한다.
Gradient Descent pitfalls
Weight
초기값1
Weight
초기값2
© 2020, Amazon Web Services, Inc. or its Affiliates.
Batch
Gradient Decent
Stochastic
Gradient Decent
full-batch
mini-batch
mini-batch
mini-batch
mini-batch
mini-batch
mini-batch
mini-batch
mini-batch
기울기를 계산 할 때, 몇 개의 입력 데이터를 사용할 것인지?
전체 m개의
데이터 사용
n개 데이터(작은 묶음) 사용
(n=1: Stochastic,
1< n < m: Mini-Batch)
batch size = m batch size = 1
batch size = n
© 2020, Amazon Web Services, Inc. or its Affiliates.
최적화를 이용한 기계 학습의 문제 풀이 과정
f(x) = W*x + b
House Price
Prediction
Guessing
Value
Actual
Value
Real-World
Problem
최적화
Objective Function
ML Model
Gradient Descent
© 2020, Amazon Web Services, Inc. or its Affiliates.
학습(Training)의 최종 목표
한번도 본적이 없는 문제를 잘 푸는 것
학습 모의 평가 최종 평가
© 2020, Amazon Web Services, Inc. or its Affiliates.
데이터 나누기
전체 데이터
Training Test
Training Validation
한번도 본적 없는 문제를 잘 풀 수 있도록 훈련 시키기 위해서 데이터를 나눈다
“훈련은 실전처럼, 실전은 훈련처럼”
© 2020, Amazon Web Services, Inc. or its Affiliates.
2 가지 질문
Q1. 모델은 복잡할 수록 좋을까?
예)
Q2. 문제를 해결할 때, 1가지 모델만 사용해야 하는 것인가?
2개 이상의 모델을 사용할 수 없을까?
© 2020, Amazon Web Services, Inc. or its Affiliates.
단순한 모델 vs. 복잡한 모델이 어느 것이 좋을까?
© 2020, Amazon Web Services, Inc. or its Affiliates.
Model Selection: Overfitted vs. Underfitted
Underfitted Overfitted
Good Fit/Robust
© 2020, Amazon Web Services, Inc. or its Affiliates.
앙상블(Ensemble): Weak Learner의 결합
Cancer
No Cancer
Cancer
Cancer
New patient
New patient
Machine Learning Model1
Machine Learning Model2
Machine Learning Modeln
∑ Ensemble’s prediction
(e.g., majority vote)
© 2020, Amazon Web Services, Inc. or its Affiliates.
Deep Learning ⊂ Machine Learning
Artificial Intelligence
Machine Learning
Deep
Learning
© 2020, Amazon Web Services, Inc. or its Affiliates.
Artificial Neuron
자
극
전
달
© 2020, Amazon Web Services, Inc. or its Affiliates.
Perceptron – 생물학적 뉴런의 수학적 모형 (인공 뉴런)
x1
x2
out
가중합
활성화
함수
W1
W2
b
예: sigmoid
출력
입력
© 2020, Amazon Web Services, Inc. or its Affiliates.
Deep Neural Network
shallow network
(세로 쌓기)
deep network
(가로-세로 쌓기)
=
© 2020, Amazon Web Services, Inc. or its Affiliates.
Deep Neural Network
=
입력층 출력층
은닉층1 은닉층2 은닉층3
© 2020, Amazon Web Services, Inc. or its Affiliates.
Deep Learning – 무수히 많은 가중치(Weight) 계산 필요!
Data Model
ML
Algorithm
숫자
0, 1, 2,..
0.01, 0.02,..
001, 010, 011, ..
model
{w1, w2, …, wn, b}
f(x) = w1*x1 + w2*x2 + … + wn*xn + b
= W*x + b
ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법
인공 뉴런
Deep Neural Network
© 2020, Amazon Web Services, Inc. or its Affiliates.
자동 미분(Autodiff) - Backpropagation
Machine Learning
f(x) = W*x + b
미분 값을
직접 계산
Real-World Problem
(e.g. House Price Prediction)
Deep Learning
f(x) = W*x + b 계산 그래프 순회
자동 미분
계산
© 2020, Amazon Web Services, Inc. or its Affiliates.
미분 값을
직접 계산
계산 그래프
backward 순회
계산 그래프
forward 순회
Machine Learning Deep Learning
© 2020, Amazon Web Services, Inc. or its Affiliates.
Deep Learning Framework = 자동 미분(Autodiff) Framework
© 2020, Amazon Web Services, Inc. or its Affiliates.
Why GPUs are more suited for Deep Learning?
CPU GPU
Deep Neural Network
무수히 많은 가중치 계산
© 2020, Amazon Web Services, Inc. or its Affiliates.
End-to-End 학습
Machine Learning
Deep Learning
© 2020, Amazon Web Services, Inc. or its Affiliates.
Machine Learning or Deep Learning?
Entities are not to be multiplied without necessity.
쓸데 없이 복잡하게 만들지 말라.
All things being equal, the simplest solution tends to be the best one.
모든 것이 같다면 가장 단순한 해가 가장 좋다.
- Occam’s Razor
© 2020, Amazon Web Services, Inc. or its Affiliates.
Summary
• Machine Learning
▪ 현실 문제 → 수학 모형(모델) → 모수 (Parameter, 가중치) 추정
• Feature Engineering: 입력 데이터 → 숫자 변환 (Feature), One-Hot Encoding, 차원 축소/증가
• 수학 모형의 모수(Parameter) 추정 방법
▪ Loss Function (Objective, Cost Function) = Error(Guessing value – Actual value) 함수
▪ Error를 최소화 시키는 모수 (Parameter, 가중치) 찾기
▪ Gradient Descent method (경사하강법)
• Train/Validation/Test Set으로 데이터 분리 – 일반화
• ML 모델 선택 – Overfitted vs Underfitted
• 앙상블(Ensemble) – Weak Learner의 결합
• Deep Learning
▪ 현실 문제 → Deep Neural Network (수학 모형, 모델) → 무수히 많은 모수 (Parameter, 가중치) 추정
▪ Deep Neural Network (DNN) - 인공 뉴런(Perceptron)을 가로-세로 방향으로 쌓아서 연결한 그래프(Network)
▪ 인공 뉴런 (Perceptron) – 생물학적 뉴런의 수학적 모형 (입력과 가중치의 곱셈합 + 편향 → 활성화 함수)
▪ 자동 미분 (Autodiff) - 계산 그래프 순회 (backpropagation) 방식으로 미분 자동 계산

Contenu connexe

Tendances

Slide3.ppt
Slide3.pptSlide3.ppt
Slide3.ppt
butest
 
★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis
irisshicat
 

Tendances (20)

Dimension Reduction: What? Why? and How?
Dimension Reduction: What? Why? and How?Dimension Reduction: What? Why? and How?
Dimension Reduction: What? Why? and How?
 
Getting Started with Azure AutoML
Getting Started with Azure AutoMLGetting Started with Azure AutoML
Getting Started with Azure AutoML
 
Machine Learning for Dummies
Machine Learning for DummiesMachine Learning for Dummies
Machine Learning for Dummies
 
Feature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax auditFeature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax audit
 
Decision Tree Learning
Decision Tree LearningDecision Tree Learning
Decision Tree Learning
 
Yapay Zeka ile Araçların Yakıt Tüketimi Tahmini.pptx
Yapay Zeka ile Araçların Yakıt Tüketimi Tahmini.pptxYapay Zeka ile Araçların Yakıt Tüketimi Tahmini.pptx
Yapay Zeka ile Araçların Yakıt Tüketimi Tahmini.pptx
 
Support Vector machine
Support Vector machineSupport Vector machine
Support Vector machine
 
Slide3.ppt
Slide3.pptSlide3.ppt
Slide3.ppt
 
Machine Learning and Data Mining: 04 Association Rule Mining
Machine Learning and Data Mining: 04 Association Rule MiningMachine Learning and Data Mining: 04 Association Rule Mining
Machine Learning and Data Mining: 04 Association Rule Mining
 
Bayesian Neural Networks
Bayesian Neural NetworksBayesian Neural Networks
Bayesian Neural Networks
 
Genetic algorithm
Genetic algorithmGenetic algorithm
Genetic algorithm
 
Introduction to Random Forest
Introduction to Random Forest Introduction to Random Forest
Introduction to Random Forest
 
Tensorflow
TensorflowTensorflow
Tensorflow
 
Handling Imbalanced Data: SMOTE vs. Random Undersampling
Handling Imbalanced Data: SMOTE vs. Random UndersamplingHandling Imbalanced Data: SMOTE vs. Random Undersampling
Handling Imbalanced Data: SMOTE vs. Random Undersampling
 
Deep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter Tuning
 
Understanding Random Forests: From Theory to Practice
Understanding Random Forests: From Theory to PracticeUnderstanding Random Forests: From Theory to Practice
Understanding Random Forests: From Theory to Practice
 
XGBoost @ Fyber
XGBoost @ FyberXGBoost @ Fyber
XGBoost @ Fyber
 
★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis
 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World Applications
 
Machine learning with scikitlearn
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearn
 

Similaire à 1시간만에 머신러닝 개념 따라 잡기

Similaire à 1시간만에 머신러닝 개념 따라 잡기 (20)

Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)
 
Machine Learning 101 - AWS Machine Learning Web Day
Machine Learning 101 - AWS Machine Learning Web DayMachine Learning 101 - AWS Machine Learning Web Day
Machine Learning 101 - AWS Machine Learning Web Day
 
Introduction to Sagemaker
Introduction to SagemakerIntroduction to Sagemaker
Introduction to Sagemaker
 
Machine Learning Fundamentals
Machine Learning FundamentalsMachine Learning Fundamentals
Machine Learning Fundamentals
 
Building Content Recommendation Systems using MXNet Gluon
Building Content Recommendation Systems using MXNet GluonBuilding Content Recommendation Systems using MXNet Gluon
Building Content Recommendation Systems using MXNet Gluon
 
Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...
Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...
Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...
 
An introduction to Machine Learning with scikit-learn (October 2018)
An introduction to Machine Learning with scikit-learn (October 2018)An introduction to Machine Learning with scikit-learn (October 2018)
An introduction to Machine Learning with scikit-learn (October 2018)
 
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
 
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
 
Deep Dive Amazon SageMaker
Deep Dive Amazon SageMakerDeep Dive Amazon SageMaker
Deep Dive Amazon SageMaker
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
深入淺出 AWS AI
深入淺出 AWS AI深入淺出 AWS AI
深入淺出 AWS AI
 
From notebook to production with Amazon Sagemaker
From notebook to production with Amazon SagemakerFrom notebook to production with Amazon Sagemaker
From notebook to production with Amazon Sagemaker
 
2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net
 
2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net
 
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
 
Amazon SageMaker
Amazon SageMakerAmazon SageMaker
Amazon SageMaker
 
Ml intro
Ml introMl intro
Ml intro
 
Ml intro
Ml introMl intro
Ml intro
 
AI/ML Powered Personalized Recommendations in Gaming Industry
AI/ML PoweredPersonalized Recommendations in Gaming IndustryAI/ML PoweredPersonalized Recommendations in Gaming Industry
AI/ML Powered Personalized Recommendations in Gaming Industry
 

Plus de Sungmin Kim

Plus de Sungmin Kim (14)

Build Computer Vision Applications with Amazon Rekognition and SageMaker
Build Computer Vision Applications with Amazon Rekognition and SageMakerBuild Computer Vision Applications with Amazon Rekognition and SageMaker
Build Computer Vision Applications with Amazon Rekognition and SageMaker
 
Introduction to Amazon Athena
Introduction to Amazon AthenaIntroduction to Amazon Athena
Introduction to Amazon Athena
 
End-to-End Machine Learning with Amazon SageMaker
End-to-End Machine Learning with Amazon SageMakerEnd-to-End Machine Learning with Amazon SageMaker
End-to-End Machine Learning with Amazon SageMaker
 
AWS re:Invent 2020 Awesome AI/ML Services
AWS re:Invent 2020 Awesome AI/ML ServicesAWS re:Invent 2020 Awesome AI/ML Services
AWS re:Invent 2020 Awesome AI/ML Services
 
AWS Personalize 중심으로 살펴본 추천 시스템 원리와 구축
AWS Personalize 중심으로 살펴본 추천 시스템 원리와 구축AWS Personalize 중심으로 살펴본 추천 시스템 원리와 구축
AWS Personalize 중심으로 살펴본 추천 시스템 원리와 구축
 
Starup을 위한 AWS AI/ML 서비스 활용 방법
Starup을 위한 AWS AI/ML 서비스 활용 방법Starup을 위한 AWS AI/ML 서비스 활용 방법
Starup을 위한 AWS AI/ML 서비스 활용 방법
 
Choose Right Stream Storage: Amazon Kinesis Data Streams vs MSK
Choose Right Stream Storage: Amazon Kinesis Data Streams vs MSKChoose Right Stream Storage: Amazon Kinesis Data Streams vs MSK
Choose Right Stream Storage: Amazon Kinesis Data Streams vs MSK
 
Octember on AWS (Revised Edition)
Octember on AWS (Revised Edition)Octember on AWS (Revised Edition)
Octember on AWS (Revised Edition)
 
Realtime Analytics on AWS
Realtime Analytics on AWSRealtime Analytics on AWS
Realtime Analytics on AWS
 
Amazon Athena 사용 팁
Amazon Athena 사용 팁Amazon Athena 사용 팁
Amazon Athena 사용 팁
 
AWS Analytics Immersion Day - Build BI System from Scratch (Day1, Day2 Full V...
AWS Analytics Immersion Day - Build BI System from Scratch (Day1, Day2 Full V...AWS Analytics Immersion Day - Build BI System from Scratch (Day1, Day2 Full V...
AWS Analytics Immersion Day - Build BI System from Scratch (Day1, Day2 Full V...
 
Databases & Analytics AWS re:invent 2019 Recap
Databases & Analytics AWS re:invent 2019 RecapDatabases & Analytics AWS re:invent 2019 Recap
Databases & Analytics AWS re:invent 2019 Recap
 
Octember on AWS
Octember on AWSOctember on AWS
Octember on AWS
 
AI/ML re:invent 2019 recap at Delivery Hero Korea
AI/ML re:invent 2019 recap at Delivery Hero KoreaAI/ML re:invent 2019 recap at Delivery Hero Korea
AI/ML re:invent 2019 recap at Delivery Hero Korea
 

Dernier

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
JoseMangaJr1
 
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
amitlee9823
 
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
amitlee9823
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
amitlee9823
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
amitlee9823
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
amitlee9823
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
amitlee9823
 

Dernier (20)

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
 
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
 
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
 
hybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptxhybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptx
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
 

1시간만에 머신러닝 개념 따라 잡기

  • 1. © 2020, Amazon Web Services, Inc. or its Affiliates. Sungmin, Kim AWS Solutions Architect 1시간 만에 머신 러닝 개념 따라잡기
  • 2. © 2020, Amazon Web Services, Inc. or its Affiliates. Agenda • Machine Learning 이란? • Machine Learning으로 풀 수 있는 문제 유형 • Machine Learning 작업 순서 • ML 학습을 위한 입력 데이터 가공하기 - Feature Engineering • ML과 최적화 문제 - Loss Function & Gradient Decent method (경사하강법) • ML 학습 속도와 모델 성능 향상을 위한 Hyper Parameter Tuning • 미래를 위한 준비 - 데이터 나누기 (Train/Validation/Test) • ML 모델 선택 시 주의할 점 - Overfitting vs. Underfitting • 여러 가지 ML 모델 결합 하기 - Ensemble method • Deep Learning
  • 3. © 2020, Amazon Web Services, Inc. or its Affiliates. Marketing Offer On A New Product
  • 4. © 2020, Amazon Web Services, Inc. or its Affiliates. Option 1- Build A Rule Engine Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Input Output Age Gender Purchase Date Items 30 M 3/1/2017 Toy …. …… ….. ….. Rule 1: 15 <age< 30 Rule 2: Bought Toy=Y, Last Purchase<30 days Rule 3: Gender = ‘M’, Bought Toy =‘Y’ Rule 4: …….. Rule 5: …….. Human Programmer
  • 5. © 2020, Amazon Web Services, Inc. or its Affiliates. Model Output Historical Purchase Data (Training Data) Prediction Age Gender Items 35 F 39 M Toy Input - New Unseen Data Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Learning Algorithm Option 2 - Learn The Business Rules From Data
  • 6. © 2020, Amazon Web Services, Inc. or its Affiliates. We Call This Approach Machine Learning Model Output Historical Purchase Data (Training Data) Prediction Age Gender Items 35 F 39 M Toy Input - New Unseen Data Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Rule 1: 15 <age< 30 Rule 2: Bought Toy=Y, Last Purchase<30 days Rule 3: Gender = ‘M’, Bought Toy =‘Y’ Rule 4: …….. Rule 5: …….. Human Programmer Learning Algorithm
  • 7. © 2020, Amazon Web Services, Inc. or its Affiliates. Classical Programming Machine Learning Data Rules Data Answers Answers Rules Machine Learning: Paradigm Shift
  • 8. © 2020, Amazon Web Services, Inc. or its Affiliates. What is Learning Algorithm? Input X (size of house) Output Y (price) f(x) = W*x + b xo xn 2 3 1
  • 9. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Algorithm f(x) = W*x + b • W = ? • b = ? 모델 학습 대상 Size (X) 2104 1600 2400 1416 3000 1985 1534 1427 1380 1494 Price (y) 400 330 369 232 540 300 315 199 212 243 ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ Input X (size of house) Output Y (Price) 2 3 1 (1), (2), (3) 중 가장 적합한(fit) 것은? Dataset
  • 10. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Algorithm f(x) = W*x + b • W = ? • b = ? 모델 학습 대상 Size (X) 2104 1600 2400 1416 3000 1985 1534 1427 1380 1494 Price (y) 400 330 369 232 540 300 315 199 212 243 (1), (2), (3) 중 가장 적합한(fit) 것은? Dataset • 입력 데이터는 모두 숫자이다. • ML의 모델은 수학적 모형(수식) 이다. • ML의 결과물은 수식의 매개변수 이다.
  • 11. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Algorithm Input Data Model Program ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1, w2, …, wn, b} f(x) = w1*x1 + w2*x2 + … + wn*xn + b = W*x + b ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법 Output
  • 12. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning으로 풀 수 있는 문제 유형 Supervised Unsupervised 정답? Prediction Classification Clustering Reinforcement • Linear Regression • Logistic Regression • SVM • K-NN • XGBoost • K-Means • DBScan Density Estimation • PCA • t-SNE Yes No • Monte Carlo • Q-Learning • DQN
  • 13. © 2020, Amazon Web Services, Inc. or its Affiliates. Supervised Learning It is a cat. No, it’s a Labrador. • The algorithm is given a set of training examples where the data and target are known. It can then predict the target value for new datasets, containing the same attributes • Human intervention and validation required Example: Photo classification and tagging
  • 14. © 2020, Amazon Web Services, Inc. or its Affiliates. Supervised Learning – How Machines Learn Human intervention and validation required e.g. Photo classification and tagging Input Label Machine Learning Algorithm Labrador Prediction Cat Training Data ? Label Labrador Adjust Model
  • 15. © 2020, Amazon Web Services, Inc. or its Affiliates. Unsupervised Learning Input Machine Learning Algorithm Prediction • Algorithm is given mass amounts of data, and it must find patterns and relationships between the data. It can then draw inferences from datasets • Human intervention is not required Example: Auto-classification of documents based on context
  • 16. © 2020, Amazon Web Services, Inc. or its Affiliates. Reinforcement Learning Action Environment State Rewards Agent
  • 17. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Use Cases Supervised Learning Ø Classification • Spam detection • Customer churn prediction Ø Regression • House price prediction • Demand forecasting Unsupervised Learning Ø Clustering • Customer segmentation Reinforcement Learning Ø Self Driving Car Ø Robots
  • 18. © 2020, Amazon Web Services, Inc. or its Affiliates. 기계 학습 유형 Supervised Unsupervised 정답? Prediction Classification Clustering Reinforcement • Linear Regression • Logistic Regression • SVM • K-NN • XGBoost • K-Means • DBScan Density Estimation • PCA • t-SNE Yes No • Monte Carlo • Q-Learning • DQN
  • 19. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Workflow 현실 문제를 Machine Learning을 이용해서 어떻게 풀 수 있을까? ML Problem Framing Raw Data Real-World Problem Define ML Problem Data Preparation Build Training Deploy
  • 20. © 2020, Amazon Web Services, Inc. or its Affiliates. ML Problem Framing 현실 문제 ML 문제 집 값 예측 (1) 어떤 ML 문제 유형인지 파악 • 예측 • 분류 • 군집화 • …. 입력 (X) • 방 개수 • 방 크기 • 위치 • 준공 연도 • 주변 시설 • … 집 값 (y) (2) 입력/출력 설계 ✓ Prediction (Supervised Learning)
  • 21. © 2020, Amazon Web Services, Inc. or its Affiliates. ML 문제 분류 Predict or forecast a value? Unsupervised Learning Supervised Learning Classification Regression Clustering Density estimation Yes No Discrete target value Continuous target value Fit data into discrete groups Numeric estimate to fit https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
  • 22. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning: Input 설계 Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1, w2, …, wn, b} f(x) = w1*x1 + w2*x2 + … + wn*xn + b = W*x + b ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법
  • 23. © 2020, Amazon Web Services, Inc. or its Affiliates. 모든 입력 데이터는 숫자(Number) 손 글씨 이미지 숫자
  • 24. © 2020, Amazon Web Services, Inc. or its Affiliates. 모든 입력 데이터는 숫자(Number) 문자열 또는 카테고리 데이터는 One-Hot Encoding 방식을 이용해서 숫자로 변환 상품 분류 가격 TV 1,000,000 냉장고 1,500,000 전자렌지 200,000 컴퓨터 800,000 선풍기 100,000 선풍기 100,000 믹서 50,000 믹서 50,000 상품 분류 가격 0 1,000,000 1 1,500,000 4 200,000 5 800,000 3 100,000 3 100,000 2 50,000 2 50,000 TV 냉장고 믹서 선풍기 전자렌지 컴퓨터 가격 1 0 0 0 0 0 1,000,000 0 1 0 0 0 0 1,500,000 0 0 0 0 1 0 200,000 0 0 0 0 0 1 800,000 0 0 0 1 0 0 100,000 0 0 0 1 0 0 100,000 0 0 1 0 0 0 50,000 0 0 1 0 0 0 50,000 원본 데이터 숫자 인코딩 One-Hot 인코딩
  • 25. © 2020, Amazon Web Services, Inc. or its Affiliates. Feature: 숫자로 변환된 ML 알고리즘의 입력 데이터
  • 26. © 2020, Amazon Web Services, Inc. or its Affiliates. Feature Engineering • 입력 데이터를 숫자로 변환하기 ex) One-Hot Encoding • 데이터의 가지 수 (차원)를 줄이거나 늘리는 작업 • 불필요한 데이터를 제거하기 • 누락된 데이터를 채워 넣기 • … 1차원 2차원 6 차원 Feature
  • 27. © 2020, Amazon Web Services, Inc. or its Affiliates. 차원의 저주 (Curse of Dimensionality) … … 1차원 2차원 3 차원 4 차원 … … … … 13 차원 784 차원 54877 차원 Iris MNIST Farm Ads 꽃받침 길이, 꽃받침 너비, 꽃잎 길이, 꽃잎 너비 pixel1, pixel2, …, pixel784 단어1, 단어2, …, 단어54877
  • 28. © 2020, Amazon Web Services, Inc. or its Affiliates. 모델 평가 Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1, w2, …, wn, b} f(x) = w1*x1 + w2*x2 + … + wn*xn + b = W*x + b ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법 ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ Input X (size of house) Output Y (Price) 2 3 1 Q) (1), (2), (3) 중 가장 적합한(fit) 것은?
  • 29. © 2020, Amazon Web Services, Inc. or its Affiliates. Input X (size of house) Loss Function (Objective Function) Output Y (Price) f(x) = W*x + b Error (f(Xj) – Yj) Loss(W, b) = ∑(f(xj) – yj)2 1 n j=1 n xo xn Mean Square Error(MSE) Function Guessing Value Actual Value
  • 30. © 2020, Amazon Web Services, Inc. or its Affiliates. Loss Function (Objective Function) 선형 회귀 문제 선형 회귀를 위한 목적 함수 • 𝑓!(𝐱")는 예측함수의 출력, yi는 예측함수가 맞추어야 하는 목표 값 • 𝑓!(𝐱") - yi는 오차 = 평균제곱오차MSE(mean squared error)
  • 31. © 2020, Amazon Web Services, Inc. or its Affiliates. Loss Function (Objective Function) 선형 회귀 문제 선형 회귀를 위한 목적 함수 • 𝑓!(𝐱")는 예측함수의 출력, yi는 예측함수가 맞추어야 하는 목표 값 • 𝑓!(𝐱") - yi는 오차 = 평균제곱오차MSE(mean squared error) 처음에는 최적 매개변수 값을 알 수 없으므로 임의 값으로 Θ! = 𝑤!, 𝑏! 설정 à Θ" = 𝑤", 𝑏" 로 개선 à Θ# = 𝑤#, 𝑏# 로 개선 à Θ#는 최적해 & Θ • 이때 𝐽 Θ# > 𝐽 Θ$ > 𝐽 Θ%
  • 32. © 2020, Amazon Web Services, Inc. or its Affiliates. Plotting Loss Function (Single Variable) W Loss (W) Minimum loss
  • 33. © 2020, Amazon Web Services, Inc. or its Affiliates. Optimization - Minimize Loss Function W Minimum loss 현 지점의 기울기 (Partial Derivative) Loss를 낮추는 방향(Descent) WJ WJ+1 Gradient Descent Wj+1 = Wj 𝛼 Loss(Wj) ∂ ∂Wj Random initial value Loss (W) 𝛼 한 발자국 크기 (Learning Rate)
  • 34. © 2020, Amazon Web Services, Inc. or its Affiliates. Gradient Decent: 최적화 문제 해결법 Learning Step weight의 업데이트 = 에러 낮추는 방향 x 한 발자국 크기 x 현 지점의 기울기 (decent) (learning rate) (gradient) Loss function의 현재 가중치에서 기울기(gradient)를 구해서 Loss를 줄이는 방향으로 가중치를 업데이트해 나간다 Learning Rate
  • 35. © 2020, Amazon Web Services, Inc. or its Affiliates. Hyper Parameter Learning Rate(학습률)는 어떻게 설정해야할까? Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1, w2, …, wn, b} f(x) = w1*x1 + w2*x2 + … + wn*xn + b = W*x + b Gradient Descent 알고 싶은 값 (Parameter) 모델 학습을 위해서 미리 알아야 하는 값 (Hyperparameter)
  • 36. © 2020, Amazon Web Services, Inc. or its Affiliates. small learning rate right learning rate large learning rate Hyper Parameter Tuning (HPO) (학습이) 너무 느리다 답을 찾지 못한다
  • 37. © 2020, Amazon Web Services, Inc. or its Affiliates. Weight 초기값, Learning Rate 등을 적절하게 선택해야한다. Gradient Descent pitfalls Weight 초기값1 Weight 초기값2
  • 38. © 2020, Amazon Web Services, Inc. or its Affiliates. Batch Gradient Decent Stochastic Gradient Decent full-batch mini-batch mini-batch mini-batch mini-batch mini-batch mini-batch mini-batch mini-batch 기울기를 계산 할 때, 몇 개의 입력 데이터를 사용할 것인지? 전체 m개의 데이터 사용 n개 데이터(작은 묶음) 사용 (n=1: Stochastic, 1< n < m: Mini-Batch) batch size = m batch size = 1 batch size = n
  • 39. © 2020, Amazon Web Services, Inc. or its Affiliates. 최적화를 이용한 기계 학습의 문제 풀이 과정 f(x) = W*x + b House Price Prediction Guessing Value Actual Value Real-World Problem 최적화 Objective Function ML Model Gradient Descent
  • 40. © 2020, Amazon Web Services, Inc. or its Affiliates. 학습(Training)의 최종 목표 한번도 본적이 없는 문제를 잘 푸는 것 학습 모의 평가 최종 평가
  • 41. © 2020, Amazon Web Services, Inc. or its Affiliates. 데이터 나누기 전체 데이터 Training Test Training Validation 한번도 본적 없는 문제를 잘 풀 수 있도록 훈련 시키기 위해서 데이터를 나눈다 “훈련은 실전처럼, 실전은 훈련처럼”
  • 42. © 2020, Amazon Web Services, Inc. or its Affiliates. 2 가지 질문 Q1. 모델은 복잡할 수록 좋을까? 예) Q2. 문제를 해결할 때, 1가지 모델만 사용해야 하는 것인가? 2개 이상의 모델을 사용할 수 없을까?
  • 43. © 2020, Amazon Web Services, Inc. or its Affiliates. 단순한 모델 vs. 복잡한 모델이 어느 것이 좋을까?
  • 44. © 2020, Amazon Web Services, Inc. or its Affiliates. Model Selection: Overfitted vs. Underfitted Underfitted Overfitted Good Fit/Robust
  • 45. © 2020, Amazon Web Services, Inc. or its Affiliates. 앙상블(Ensemble): Weak Learner의 결합 Cancer No Cancer Cancer Cancer New patient New patient Machine Learning Model1 Machine Learning Model2 Machine Learning Modeln ∑ Ensemble’s prediction (e.g., majority vote)
  • 46. © 2020, Amazon Web Services, Inc. or its Affiliates. Deep Learning ⊂ Machine Learning Artificial Intelligence Machine Learning Deep Learning
  • 47. © 2020, Amazon Web Services, Inc. or its Affiliates. Artificial Neuron 자 극 전 달
  • 48. © 2020, Amazon Web Services, Inc. or its Affiliates. Perceptron – 생물학적 뉴런의 수학적 모형 (인공 뉴런) x1 x2 out 가중합 활성화 함수 W1 W2 b 예: sigmoid 출력 입력
  • 49. © 2020, Amazon Web Services, Inc. or its Affiliates. Deep Neural Network shallow network (세로 쌓기) deep network (가로-세로 쌓기) =
  • 50. © 2020, Amazon Web Services, Inc. or its Affiliates. Deep Neural Network = 입력층 출력층 은닉층1 은닉층2 은닉층3
  • 51. © 2020, Amazon Web Services, Inc. or its Affiliates. Deep Learning – 무수히 많은 가중치(Weight) 계산 필요! Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1, w2, …, wn, b} f(x) = w1*x1 + w2*x2 + … + wn*xn + b = W*x + b ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1, w2, …, b)를 추정 하는 방법 인공 뉴런 Deep Neural Network
  • 52. © 2020, Amazon Web Services, Inc. or its Affiliates. 자동 미분(Autodiff) - Backpropagation Machine Learning f(x) = W*x + b 미분 값을 직접 계산 Real-World Problem (e.g. House Price Prediction) Deep Learning f(x) = W*x + b 계산 그래프 순회 자동 미분 계산
  • 53. © 2020, Amazon Web Services, Inc. or its Affiliates. 미분 값을 직접 계산 계산 그래프 backward 순회 계산 그래프 forward 순회 Machine Learning Deep Learning
  • 54. © 2020, Amazon Web Services, Inc. or its Affiliates. Deep Learning Framework = 자동 미분(Autodiff) Framework
  • 55. © 2020, Amazon Web Services, Inc. or its Affiliates. Why GPUs are more suited for Deep Learning? CPU GPU Deep Neural Network 무수히 많은 가중치 계산
  • 56. © 2020, Amazon Web Services, Inc. or its Affiliates. End-to-End 학습 Machine Learning Deep Learning
  • 57. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning or Deep Learning? Entities are not to be multiplied without necessity. 쓸데 없이 복잡하게 만들지 말라. All things being equal, the simplest solution tends to be the best one. 모든 것이 같다면 가장 단순한 해가 가장 좋다. - Occam’s Razor
  • 58. © 2020, Amazon Web Services, Inc. or its Affiliates. Summary • Machine Learning ▪ 현실 문제 → 수학 모형(모델) → 모수 (Parameter, 가중치) 추정 • Feature Engineering: 입력 데이터 → 숫자 변환 (Feature), One-Hot Encoding, 차원 축소/증가 • 수학 모형의 모수(Parameter) 추정 방법 ▪ Loss Function (Objective, Cost Function) = Error(Guessing value – Actual value) 함수 ▪ Error를 최소화 시키는 모수 (Parameter, 가중치) 찾기 ▪ Gradient Descent method (경사하강법) • Train/Validation/Test Set으로 데이터 분리 – 일반화 • ML 모델 선택 – Overfitted vs Underfitted • 앙상블(Ensemble) – Weak Learner의 결합 • Deep Learning ▪ 현실 문제 → Deep Neural Network (수학 모형, 모델) → 무수히 많은 모수 (Parameter, 가중치) 추정 ▪ Deep Neural Network (DNN) - 인공 뉴런(Perceptron)을 가로-세로 방향으로 쌓아서 연결한 그래프(Network) ▪ 인공 뉴런 (Perceptron) – 생물학적 뉴런의 수학적 모형 (입력과 가중치의 곱셈합 + 편향 → 활성화 함수) ▪ 자동 미분 (Autodiff) - 계산 그래프 순회 (backpropagation) 방식으로 미분 자동 계산