Baby Machine Learning - Speaker Deck

Baby Machine Learning

by Buzzvil

Embed

Start on current slide

Slide 1

Slide 1 text

Hes 2021-06-23 Baby Machine Learning From Regression To Neural Network

Slide 2

Slide 2 text

Machine Learning •AI •Deep Learning •Classi fi cation •Regression •Clustering •Data Mining •Reinforcement Learning ...umm "MATH"

Slide 3

Slide 3 text

Machine Learning •AI •Deep Learning •Classi fi cation •Regression •Clustering •Data Mining •Reinforcement Learning ...umm "MATH"

Slide 4

Slide 4 text

How people think about House price • How many people? • How Big? • How many rooms & bathrooms? • Where the house is? + ठࣁӂ, ৉ࣁӂ

Slide 5

Slide 5 text

How people think about House price - Relation • How many people? • Size • # Rooms & Bathrooms • Where the house is? • How Big? • ठࣁӂ • ৉ࣁӂ • Family Size • Safety

Slide 6

Slide 6 text

How people think about House price - Priority • How many people? • Size • # Rooms & Bathrooms • Where the house is? • How Big? • ठࣁӂ • ৉ࣁӂ • Family Size • Safety 1

Slide 7

Slide 7 text

How people think about House price - Priority • How many people? • Size • # Rooms & Bathrooms • Where the house is? • How Big? • ठࣁӂ • ৉ࣁӂ • Family Size • Safety 1 Depends on a situation

Slide 8

Slide 8 text

Demand makes Price How people think about

Slide 9

Slide 9 text

Demand makes Price How people think about

Slide 10

Slide 10 text

makes Price Various Situation How people think about

Slide 11

Slide 11 text

Data Various Situation How people think about

Slide 12

Slide 12 text

Learn Method from Model variable Brain Data How people think about

Slide 13

Slide 13 text

Let's start with simple model

Slide 14

Slide 14 text

What makes price Overview Location point • ठࣁӂ • ৉ࣁӂ • Safety • Family Size • Size • Rooms &BR Volume point Family point Price

Slide 15

Slide 15 text

What makes price Overview Location point • ठࣁӂ • ৉ࣁӂ • Safety • Family Size • Size • Rooms &BR Volume point Family point Price

Slide 16

Slide 16 text

Linear Regression House price • ठࣁӂ • ৉ࣁӂ • Safety ? ? ? • Family Size ? Location Point

Slide 17

Slide 17 text

Linear Regression House price • ठࣁӂ • ৉ࣁӂ • Safety ? ? ? • Family Size ? Location Point Safetyо 95, ठࣁӂ੉ 1(True), ৉ࣁӂ 0(False), Family Sizeо 4ݺ੉ݶ, Location pointח 77੼੉ ա৬ঠ ೞפө... ੉ۧѱ ߄Լ઱ݶ!

Slide 18

Slide 18 text

Linear Regression House price • ठࣁӂ • ৉ࣁӂ • Safety ? ? ? • Family Size ? Location Point Ӓېࢲ ӒѦ ־о ೞחؘ?! ৘ஏ Ѿҗ৬ पઁ чਸ ઴ৈ઱ח ੌਸ.. Optimizerо ೞݶ غѷ׮!!

Slide 19

Slide 19 text

Slide 20

Slide 20 text

Linear Regression Happy case

Slide 21

Slide 21 text

Linear Regression Umm.. case

Slide 22

Slide 22 text

Activation Fuction move on from Linear Linear Regression = Non-Linear Result + Activation(nonlinearities)

Slide 23

Slide 23 text

Activation Fuction move on from Linear Linear Regression = Non-Linear Result + Activation(nonlinearities)

Slide 24

Slide 24 text

σ( ) Location point Logistic Regression House price =

Slide 25

Slide 25 text

σ( ) Location point Logistic Regression House price • ठࣁӂ • ৉ࣁӂ • Safety ? ? ? • Family Size ? Good / Not Good (Location) = աח ݅઒ೡ ഛܫਸ ঌҊ रয.. Ӓېࢲ ഛܫ਷?

Slide 26

Slide 26 text

Neural Network House price - Stack the regression a( ) Location point • ठࣁӂ • ৉ࣁӂ • Safety • Family Size • Size • Rooms &BR a( ) Volume point a( ) Family point Price

Slide 27

Slide 27 text

Neural Network House price - Stack the regression a( ) Location point • ठࣁӂ • ৉ࣁӂ • Safety • Family Size • Size • Rooms &BR a( ) Volume point a( ) Family point Prob σ( )

Slide 28

Slide 28 text

Neural Network House price - Stack the regression a( ) Location point • ठࣁӂ • ৉ࣁӂ • Safety • Family Size • Size • Rooms &BR a( ) Volume point a( ) Family point Prob σ( ) Prob σ( ) Prob σ( ) ARGMAX

Slide 29

Slide 29 text

What we can do • Probability of Conversion • Classi fi cation • Scoring • Ranking …

Slide 30

Slide 30 text

ೞ૑݅ ৈ੹൤ য۵׮..