Expectation Maximization. Coin flipping experiment  Diberikan koin A dan B dengan nilai bias A dan B yang belum diketahui  Koin A akan memunculkan head.

Slides:



Advertisements
Presentasi serupa
Pengujian Hipotesis.
Advertisements

Pendugaan Parameter.
EXODUS 6:6-8 6 THEREFORE SAY TO THE CHILDREN OF ISRAEL: ‘I AM THE LORD; I WILL BRING YOU OUT FROM UNDER THE BURDENS OF THE EGYPTIANS, I WILL RESCUE YOU.
Model Logistik untuk Data Ordinal (Ordinal Regression)
Review : Invers Matriks
PEMBENTUKAN MODEL RLB Kuliah ke 8 anareg Dosen: usman bustaman.
Chapter 10 Marketing.
Common Effect Model.
Project Procurement Management
Measures of Association
ARRAY RUBY. PENDAHULUAN Ruby's arrays are untyped and mutable. The elements of an array need not all be of the same class, and they can be changed at.
Penyelesaian Persamaan Linier Simultan
KONSEP ULLMAN.
Proses Stokastik Semester Ganjil 2013/2014
Pertemuan 05 Sebaran Peubah Acak Diskrit
Ruang Contoh dan Peluang Pertemuan 05
1 Pertemuan 10 Statistical Reasoning Matakuliah: T0264/Inteligensia Semu Tahun: Juli 2006 Versi: 2/1.
Population and sample. Population is complete actual/theoretical collection of numerical values (scores) that are of interest to the researcher. Simbol.
Masalah Transportasi II (Transportation Problem II)
PENDUGAAN PARAMETER Pertemuan 7
Uji Goodness of Fit : Distribusi Multinomial
Pertemuan 07 Peluang Beberapa Sebaran Khusus Peubah Acak Kontinu
Verb Tense Tense denotes the time of the action indicated by a verb. The time is not always the same as that indicated by the name of the tense.
Statistika Mulaab,S,si M.kom Lab CAI Teknik Informatika xxxx Website Kuliah : mulaab.wordpress.com.
1 HAMPIRAN NUMERIK SOLUSI PERSAMAAN LANJAR Pertemuan 5 Matakuliah: K0342 / Metode Numerik I Tahun: 2006 TIK:Mahasiswa dapat meghitung nilai hampiran numerik.
1 Pertemuan 24 Contingency Planning Matakuliah:A0334/Pengendalian Lingkungan Online Tahun: 2005 Versi: 1/1.
Shear Joints under eccentric loads Joints can and should be loaded in shear so that the fasteners see no additional stress beyond the initial tightening.
4- Classification: Logistic Regression 9 September 2015 Intro to Logistic Regression.
Chapter 5 Discrete Random Variables and Probability Distributions Statistika.
Keuangan dan Akuntansi Proyek Modul 2: BASIC TOOLS CHRISTIONO UTOMO, Ph.D. Bidang Manajemen Proyek ITS 2011.
Jartel, Sukiswo Sukiswo
STATISTIKA CHATPER 4 (Perhitungan Dispersi (Sebaran))
Statistik TP A Pengujian Hipotesis Satu Populasi (Mean dan Proporsi)
Pert. 16. Menyimak lingkungan IS/IT saat ini
KOMUNIKASI DATA Materi Pertemuan 3.
Induksi Matematika.
07/11/2017 BARISAN DAN DERET KONSEP BARISAN DAN DERET 1.
KONSEP DASAR PROBABILITAS
Konsep pemrograman LOOP
User (Pengguna) User = a person who use an IRS
Uji Goodness of Fit : Distribusi Multinomial
Statistika Chapter 4 Probability.
Pengujian Hipotesis (I) Pertemuan 11
Matakuliah : I0014 / Biostatistika Tahun : 2005 Versi : V1 / R1
Presentasi Statistika Dasar
Pendugaan Parameter (I) Pertemuan 9
An Editing Process: Rereading
Review Operasi Matriks
Portofolio Campuran.
PENDUGAAN PARAMETER Pertemuan 8
Pendugaan Parameter (II) Pertemuan 10
Pertemuan Kesembilan Analisa Data
Upaya Mengatasi Kecemasan dalam Menghadapi Masa Depan
Manajemen Proyek Perangkat Lunak (MPPL)
Pengantar Probabilitas
Matematika PERSAMAAN KUADRAT Quadratic Equations Quadratic Equations
ENGINEERING SCIENCE IS ABOUT SOLVING PROBLEMS
TEORI PROBABILITAS by WAHYUYANTI (WYT)
Evidence-Based Medicine Prof. Carl Heneghan Director CEBM University of Oxford.
Simultaneous Linear Equations
ENGINEERING RESEARCH IS A QUANTITATIVE RESEARCH
Aplikasi Graph Minimum Spaning Tree Shortest Path.
THE INFORMATION ABOUT HEALTH INSURANCE IN AUSTRALIA.
HughesNet was founded in 1971 and it is headquartered in Germantown, Maryland. It is a provider of satellite-based communications services. Hughesnet.
 Zoho Mail offers easy options to migrate data from G Suite or Gmail accounts. All s, contacts, and calendar or other important data can be imported.
How do I Add or Remove a delegate to my Gmail account? Google launched delegation service 9 years ago for Gmail that allows you to give permission to access.
HANDLING RUSH PRESIDENT UNIVERSITY NURLAELA RIZKINA.
Probability IIntroduction to Probability ASatisfactory outcomes vs. total outcomes BBasic Properties CTerminology IICombinatory Probability AThe Addition.
Media Pembelajaran PATHWAY TO ENGLISH Kelompok Peminatan Untuk SMA/MA Kelas X.
Draw a picture that shows where the knife, fork, spoon, and napkin are placed in a table setting.
Transcript presentasi:

Expectation Maximization

Coin flipping experiment  Diberikan koin A dan B dengan nilai bias A dan B yang belum diketahui  Koin A akan memunculkan head dengan probabilitas A dan memunculkan tail dengan probabilitas 1- A, demikian juga dengan koin B  Percobaan berikut diulang lima kali : pilih secara random koin A atau B (with equal probability), dan lakukan toss sebanyak 10 kali, sehingga total ada 50 toss  Tujuan : Estimasikan A dan B  Dalam statistik, ini disebut dengan melakukan estimasi maximum likelihood

Maximum likelihood for complete data  Ketika semua random variable diketahui, yaitu hasil dari setiap coin flip dan tipe koin yang digunakan, maka hal ini disebut sebagai complete data case.  Pada complete data case, nilai A dan B dapat dihitung sbb

Maximum likelihood for complete data  Koin A akan memunculkan head dengan probabilitas A dan memunculkan tail dengan probabilitas 1- A, demikian juga dengan koin B

Incomplete data case  Bagaimana jika ada variable yang tidak diketahui -> incomplete data  Hasil dari setiap coin flip diketahui, tetapi tipe koin yang digunakan tidak diketahui  Pada kasus seperti ini, mengestimasi A dan B dapat menggunakan EM

Expectation Maximization

E step  Contoh : pada baris ke-dua 9H1T, koin mana yang likely menghasilkan ini?  Berawal dari initial parameter P(H 9 T 1 |A) be the probability of observing 9 heads, 1 tail when coin is A = 0.8 P(H 9 T 1 |B) be the probability of observing 9 heads, 1 tail when coin is B = 0.2 P(A|H 9 T 1 ) be the probability of the coin being A when you observe 9 heads, 1 tail. P(B|H 9 T 1 ) be the probability of the coin being B when you observe 9 heads, 1 tail.

P(H 9 T 1 |A) be the probability of observing 9 heads, 1 tail when coin is A = 0.8 P(H 9 T 1 |B) be the probability of observing 9 heads, 1 tail when coin is B = 0.2

 Since we calculated that proportion to be 0.8:0.2, a contribution of 0.8 ⋅ (9,1)=(7.2,0.8) is added to the column for coin A and a contribution of 0.2 ⋅ (9,1)=(1.8,0.2) is added to the column for coin B. Together, they add up to (9,1) (since we obtained the weights by normalizing their sum to 1). Thus, the more likely it seems, according to the current bias estimates, that this row was produced by coin A, the more of it we add to the column for coin A.  Note that we're not calculating an expectation value in the columns; we're merely adding up fractions of heads and tails in proportion to the likelihood that they came from this coin, and in the end we take the overall ratio of heads and tails to get a new bias estimate; there's no need for the heads and tails to add up to anything or to form an expectation value in either of the columns individually. P(H 9 T 1 |A) be the probability of observing 9 heads, 1 tail when coin is A = 0.8 P(H 9 T 1 |B) be the probability of observing 9 heads, 1 tail when coin is B = 0.2 P(A|H 9 T 1 ) be the probability of the coin being A when you observe 9 heads, 1 tail. P(B|H 9 T 1 ) be the probability of the coin being B when you observe 9 heads, 1 tail.

M Step  Menggunakan nilai bias yang baru, ulangi langkah sebelumnya sampai beberapa iterasi sehingga menghasilkan nilai bias yang konvergen

Expectation Maximization for Soft Clustering