1 Pertemuan 9 JARINGAN LEARNING VECTOR QUANTIZATION Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.

Slides:



Advertisements
Similar presentations
1 Pertemuan > > Matakuliah: >/ > Tahun: > Versi: >
Advertisements

1 Pertemuan 16 First & Second Conditionals Matakuliah: G0134 – Grammar III Tahun: 2005 Versi: revisi 1.
Teknik Enkoding Pertemuan 08 Matakuliah: H0484/Jaringan Komputer Tahun: 2007.
1 Pertemuan 12 Binary Search Tree Matakuliah: T0026/Struktur Data Tahun: 2005 Versi: 1/1.
Arsitektur Jaringan Pertemuan 09 Matakuliah: H0484/Jaringan Komputer Tahun: 2007.
1 Pertemuan 04 Proxy/Cache Matakuliah: H0491/Praktikum Jaringan Komputer Tahun: 2005 Versi: 1/0.
1 Pertemuan 22 Radix Sort Matakuliah: T0016/Algoritma dan Pemrograman Tahun: 2005 Versi: versi 2.
1 Pertemuan 15 The Business Owner’s View Matakuliah: A0194/Pengendalian Rekayasa Ulang Informasi Tahun: 2005 Versi: 1/5.
1 Pertemuan 6 Elementary UDP Sockets Matakuliah: H0483 / Network Programming Tahun: 2005 Versi: 1.0.
12 - Organisation Matakuliah: G0622/Bahasa Inggris 1 Tahun: 2005 Versi: 1.01.
5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Artificial neural networks:
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
4 1 Perceptron Learning Rule. 4 2 Learning Rules Learning Rules : A procedure for modifying the weights and biases of a network. Learning Rules : Supervised.
Competitive Networks. Outline Hamming Network.
1 Pertemuan 10 Arsitektur Jaringan Model OSI Matakuliah: H0174/Jaringan Komputer Tahun: 2006 Versi: 1/0.
1 Pertemuan 26 Object Relational Database Management System (Lanjutan) Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 23 Object database design (Lanjutan bagian 2) Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan > > Matakuliah: >/ > Tahun: > Versi: >
1 Pertemuan 13 BACK PROPAGATION Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
Neural Networks Part 4 Dan Simon Cleveland State University 1.
1 Pertemuan 24 Object database design (Lanjutan bagian 3) Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 09 Design and Production Matakuliah: T0553/Sistem Multimedia Tahun: 2005 Versi: 5.
1 Pertemuan 05 Firewall Matakuliah: H0451/Praktikum Jaringan Komputer Tahun: 2006 Versi: 1/0.
1 Pertemuan 15 ADAPTIVE RESONANCE THEORY Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
1 Pertemuan 03 Routing Matakuliah: H0451/Praktikum Jaringan Komputer Tahun: 2006 Versi: 1/0.
1 Pertemuan 02 LAN Matakuliah: H0451/Praktikum Jaringan Komputer Tahun: 2006 Versi: 1/0.
1 Pertemuan 14 Object Query Language (Lanjutan bagian 1) Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 5 The structure part of object data model Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 04 Expression Matakuliah: D0524 / Algoritma dan Pemrograman Komputer Tahun: 2005 Versi:
07 - Advertising Matakuliah: G0622/Bahasa Inggris 1 Tahun: 2005 Versi: 1.01.
1 Pertemuan 9 Making an outline Matakuliah: G1072 – Reading 1 Tahun: 2005 Versi: revisi 0.
Perceptron Learning Rule
1 Pertemuan 21 Audit Reporting Matakuliah:A0274/Pengelolaan Fungsi Audit Sistem Informasi Tahun: 2005 Versi: 1/1.
1 Pertemuan 17 Building Object Database Application Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 05 Selection Matakuliah: D0524 / Algoritma dan Pemrograman Komputer Tahun: 2005 Versi:
1 Pertemuan 01 Teknologi Jaringan Matakuliah: H0242 / Keamanan Jaringan Tahun: 2006 Versi: 1.
1 Pertemuan 11 QUIZ Matakuliah: J0274/Akuntansi Manajemen Tahun: 2005 Versi: 01/00.
11 - Innovation Matakuliah: G0622/Bahasa Inggris 1 Tahun: 2005 Versi: 1.01.
1 Pertemuan 1 Pendahuluan : Konsep Sistem Matakuliah: H0204/ Rekayasa Sistem Komputer Tahun: 2005 Versi: v0 / Revisi 1.
1 Pertemuan 06 Sebaran Penarikan Contoh Matakuliah: I0272 – Statistik Probabilitas Tahun: 2005 Versi: Revisi.
1 Pertemuan 20 Time & Condition Clauses with Future reference Matakuliah: G0134 – Grammar III Tahun: 2005 Versi: revisi 1.
1 Pertemuan 18 I wish, If only Matakuliah: G0134 – Grammar III Tahun: 2005 Versi: revisi 1.
1 Pertemuan 7 The Object Definition Language Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
1 Pertemuan 17 HOPFIELD NETWORK Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
1 Pertemuan #3 Clocks and Realtime Matakuliah: H0232/Sistem Waktu Nyata Tahun: 2005 Versi: 1/5.
1 Pertemuan 06 Repetition Matakuliah: D0524 / Algoritma dan Pemrograman Komputer Tahun: 2005 Versi:
1 Pertemuan 25 Making It Happen Matakuliah: A0194/Pengendalian Rekayasa Ulang Informasi Tahun: 2005 Versi: 1/5.
1 Pertemuan 25 Parallel Processing 1 Matakuliah: H0344/Organisasi dan Arsitektur Komputer Tahun: 2005 Versi: 1/1.
13 - Organisation Matakuliah: G0622/Bahasa Inggris 1 Tahun: 2005 Versi: 1.01.
1 Pertemuan 18 HOPFIELD DESIGN Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
1 Pertemuan 8 The Object Definition Language (Lanjutan) Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
Artificial Neural Networks
1 Pertemuan 25 Object Relational Database Management System Matakuliah: M0174/OBJECT ORIENTED DATABASE Tahun: 2005 Versi: 1/0.
IE 585 Competitive Network – Learning Vector Quantization & Counterpropagation.
CHAPTER 14 Competitive Networks Ming-Feng Yeh.
1 Pertemuan 16 The Business Owner’s View Matakuliah: A0194/Pengendalian Rekayasa Ulang Informasi Tahun: 2005 Versi: 1/5.
1 Pertemuan 8 Perenc & Peranc Sambungan Matakuliah: D0472/PERANCANGAN ELEMEN MESIN Tahun: 2005 Versi:
Pertemuan 20 The Business Views of the Technology Architecture
Table Pertemuan 10 Matakuliah : L0182 / Web & Animation Design
Pertemuan 22 The Business Views of the Technology Architecture
Pertemuan 7 JARINGAN INSTAR DAN OUTSTAR
Pertemuan 11 Model TCP/IP
Matakuliah : Web Design
Competitive Networks.
Competitive Networks.
Neuro-Computing Lecture 2 Single-Layer Perceptrons
Perceptron Learning Rule
Perceptron Learning Rule
Perceptron Learning Rule
Presentation transcript:

1 Pertemuan 9 JARINGAN LEARNING VECTOR QUANTIZATION Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1

2 Learning Outcomes Pada akhir pertemuan ini, diharapkan mahasiswa akan mampu : Mendemonstrasikan Jaringan Learning Vector Quantization

3 Outline Materi Arsitektur Jaringan Learning Rule

4 Learning Vector Quantization The net input is not computed by taking an inner product of the prototype vectors with the input. Instead, the net input is the negative of the distance between the prototype vectors and the input.

5 Subclass For the LVQ network, the winning neuron in the first layer indicates the subclass which the input vector belongs to. There may be several different neurons (subclasses) which make up each class. The second layer of the LVQ network combines subclasses into a single class. The columns of W 2 represent subclasses, and the rows represent classes. W 2 has a single 1 in each column, with the other elements set to zero. The row in which the 1 occurs indicates which class the appropriate subclass belongs to.

6 Example Subclasses 1, 3 and 4 belong to class 1. Subclass 2 belongs to class 2. Subclasses 5 and 6 belong to class 3. A single-layer competitive network can create convex classification regions. The second layer of the LVQ network can combine the convex regions to create more complex categories.

7 LVQ Learning If the input pattern is classified correctly, then move the winning weight toward the input vector according to the Kohonen rule. If the input pattern is classified incorrectly, then move the winning weight away from the input vector. LVQ learning combines competive learning with supervision. It requires a training set of examples of proper network behavior.

8 Example p = t =     p = t =    

9 First Iteration a 1 competn 1  compet w 1 1 p 1 –– w 1 2 p 1 –– w 1 3 p 1 –– w 1 4 p 1 ––          ==

10 Second Layer This is the correct class, therefore the weight vector is moved toward the input vector.

11 Figure

12 Final Decision Regions