Collabnet Overview v 1.2 021201 Informatika Introduction.

Slides:



Advertisements
Presentasi serupa
Developing Knowledge Management dalam perusahaan Week 10 – Pert 19 & 20 (Off Class Session)
Advertisements

Pengujian Hipotesis untuk Satu dan Dua Varians Populasi
Mata Kuliah : ALGORITMA dan STRUKTUR DATA 1.
PEMOGRAMAN BERBASIS JARINGAN
Materi Analisa Perancangan System.
Statistika Nonparametrik PERTEMUAN KE-1 FITRI CATUR LESTARI, M. Si
EKO NURSULISTIYO.  Perhatikan gambar 11 a, perahu dikenai oleh ombak dari arah kanan misalkan setiap 4 sekon dalam keadaan perahu diam. Dalam keadaan.
IT SEBAGAI ALAT UNTUK MENCIPTAKAN KEUNGGULAN KOMPETISI
INTRODUCTION TO PSYCHOLOGY. Recommended Literature 1. Introduction to Psychology : Gateway to Mind and Behavior by Dennis Coon and John O. Mitterer 2.
Tugas-Tugas.
Slide 3-1 Elmasri and Navathe, Fundamentals of Database Systems, Fourth Edition Revised by IB & SAM, Fasilkom UI, 2005 Exercises Apa saja komponen utama.
Review IS & Software System Concept Diah Priharsari PTIIK – Universitas Brawijaya Source: 1.Obrien & Marakas, Management Information.
Introduction to The Design & Analysis of Algorithms
IF-ITB/SAS/25Aug2003 IF7074 – Bagian Pertama Page 1 IF 7047 Kewirausahaan Teknologi Informasi Bagian Pertama: 1.1. Entrepreneurship, entrepreneur, dan.
Artificial Intelligence
Jaringan Syaraf Tiruan
KNOWLEDGE MANAGEMENT: philosophy, processes, and pitfalls EXTRACTED FROM Soo, Devinney, Midgley, Deering (2002) CALIFORNIA MANAGEMENT REVIEW, 44 (4) 1seri.
PROSES PADA WINDOWS Pratikum SO. Introduksi Proses 1.Program yang sedang dalam keadaan dieksekusi. 2.Unit kerja terkecil yang secara individu memiliki.
1. Objek dalam kalimat aktif menjadi subjek dalam kalimat pasif
KIMIA ORGANIK II ELFI SUSANTI VH.
Jeff Howbert Introduction to Machine Learning Winter Classification Nearest Neighbor.
Understanding The nature of PBI Courses Nury S, MA Presented at UAD workshop August 10 –
(Jaringan Syaraf Tiruan) ANN (Artificial Neural Network)
Pengantar/pengenalan (Introduction)
Could not load an object because it is not avaliable on this machine. Tidak dapat memuat sebuah benda karena tidak tersedia pada mesin ini.
Menjelaskan sifat – sifat komponen elektronika aktif dan pasif
Implementing an REA Model in a Relational Database
MEMORY Bhakti Yudho Suprapto,MT. berfungsi untuk memuat program dan juga sebagai tempat untuk menampung hasil proses bersifat volatile yang berarti bahwa.
1 Magister Teknik Perencanaan Universitas Tarumanagara General View On Graduate Program Urban & Real Estate Development (February 2009) Dr.-Ing. Jo Santoso.
2nd MEETING Assignment 4A “Exploring Grids” Assignment 4 B “Redesign Grids” Create several alternatives grid sysytem using the provided elements: (min.
BENTUK ING VERB + ING. Bentuk ING juga biasa disebut dengan ING form Meskipun pembentukannya sangat se- derhana tetapi penggunaannya mem- punyai aturan.
JARINGAN SYARAF TIRUAN
LOGO Manajemen Data Berdasarkan Komputer dengan Sistem Database.
ORGANISASI KOMPUTER Oleh : PUTRA PRIMA NAUFAL, S.ST SUMBER
Definisi VLAN Pemisahan jaringan secara logis yang dilakukan pada switch Pada tradisional switch, dalam satu switch menunjukkan satu segmentasi LAN.
MODELS OF PR SYIFA SA. Grunig's Four models of Public Relations Model Name Type of Communica tion Model Characteristics Press agentry/ publicity model.
Metodologi Penelitian dalam Bidang Informatika
3.1 © 2007 by Prentice Hall OVERVIEW Information Systems, Organizations, and Strategy.
Diagnose device problems that connected to the Wide Area Network Identify problems Through the Symptoms that arise HOME.
ARTIFICIAL INTELLEGENT
THE IMMERSED TUNNELS MAIN BENEFITS AND INNOVATION BY. WAWAN SETIAWAN.
Introduction to Softcomputing Son Kuswadi Robotic and Automation Based on Biologically- inspired Technology (RABBIT) Electronic Engineering Polytechnic.
© 2009 Fakultas Teknologi Informasi Universitas Budi Luhur Jl. Ciledug Raya Petukangan Utara Jakarta Selatan Website:
SISTEM TERDISTRIBUSI (SILABUS dan Introduction to Distributed Systems)
Menu Standard Competence Based Competence.
Tim Machine Learning PENS-ITS
Pengenalan Jaringan Syaraf Tiruan
Jaringan Syaraf Tiruan (JST)
PENGENALAN JARINGAN SYARAF TIRUAN (JST)
MULTILAYER PERCEPTRON
Artificial Neural Network (Back-Propagation Neural Network)
Pertemuan 10 Neural Network
1 Pertemuan 26 NEURO FUZZY SYSTEM Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
Artificial Intelligence Oleh Melania SM
JARINGAN SYARAF TIRUAN SISTEM BERBASIS PENGETAHUAN
Aplikasi Kecerdasan Komputasional
Anatomi Neuron Biologi
Jaringan Syaraf Tiruan
Jaringan Syaraf Tiruan
Artificial Neural Network
JARINGAN SYARAF TIRUAN
Master data Management
Database User Account.
Self-Organizing Network Model (SOM) Pertemuan 10
JARINGAN SYARAF TIRUAN
JARINGAN SYARAF TIRUAN
Minimalist Motion Planning Using Global Topological Guarantees
Face Recognition based on Radial Basis Function and Clustering Algorithm Yuanfeng Gao 2008/12/12.
What is Kerberos? Network Security.
Xuan Huo and Ming Li and Zhi-Hua Zhou
Transcript presentasi:

Collabnet Overview v Informatika Introduction

Informatika What is an ANN?  It is a computational System Inspired by Structure, Processing method, Learning ability of Biological Brain  The term “neural network” is also applied to models of the brain

Informatika Why ANN?  Some tasks can be done easily (effortlessly) by humans but are hard by conventional paradigms on Von Neumann machine with algorithmic approach  Computers can perform many operations considerably faster than a human being

Informatika Why ANN?  Massive Parallelism  Distributed representation  Learning ability  Generalization ablity  Fault tolerance

Informatika Characteristics of ANN  A large number of very simple processing neuron-like processing elements  A large number of weighted connections between the elements  Distributed representation of knowledge over the connections  Knowledge is acquired by network through a learning process

Informatika Biological Neuron  Dendrit, bertugas menerima informasi  Soma, tempat pengolahan informasi  Axon, mengirim inpuls-inpuls ke sel syaraf lainya  Synapse, penghubung antara 2 neuron

Informatika Biological vs Artificial Otak ManusiaJST SomaNode DendritesInput/Masukan AxonOutput/Keluaran SynapsisWeight/ Bobot

Informatika Artificial Neuron Σ p2p SUM w1w1 w2w2 wiwi Weight F(y) n=Σp i.w i a=f(n) Activation Function

Informatika Neuron vs Node

Informatika Topology

Informatika Learning  Learn the connection weights from a set of training examples  Different network architectures required different learning algorithms

Informatika Supervised Learing  The network is provided with a correct answer (output) for every input pattern  Weights are determined to allow the network to produce answers as close as possible to the known correct answers  The back-propagation algorithm belongs into this category

Informatika Unsupervised Learning  Does not require a correct answer associated with each input pattern in the training set  Explores the underlying structure in the data, or correlations between patterns in the data, and organizes patterns into categories from these correlations  The Kohonen algorithm belongs into this category

Informatika Applications  Pattern Classification  Clustering/Categorization  Function approximation  Prediction/Forecasting  Optimization  Content-addressable Memory  Control

Informatika Sejarah  Model JST formal pertama diperkenalkan oleh McCulloch dan Pitts (1943)  1949, Hebb mengusulkan jaringan Hebb  1958, Rosenblatt mengembangkan perceptron untuk klasifikasi pola  1960, Widrow dan Hoff mengembangkan ADALINE dengan aturan pembelajaran Least Mean Square (LMS)  1974, Werbos memperkenalkan algoritma backpropagation untuk perceptron banyak lapisan

Informatika Sejarah  1975, Kunihiko Fukushima mengembangkan JST khusus pengenalan karakter, disebut cognitron, namun gagal mengenali posisi atau rotasi karakter yang terdistorsi 1982, Kohonen mengembangkan learning unsupervised untuk pemetaan 1982, Grossberg dan Carpenter mengembangkan Adaptive Resonance Theory (ART, ART2, ART3) 1982, Hopfield mengembangkan jaringan Hopfield untuk optimasi

Informatika Sejarah 1983, perbaikan cognitron (1975) dengan neocognitron 1985, Algoritma Boltzmann untuk jaringan syaraf probabilistik 1987, dikembangkan BAM (Bidirectional Associative Memory) 1988, dikembangkan Radial Basis Function

Collabnet Overview v Informatika Thank’s Any Questions ?