KURIKULUM ITB 2013-2018 – PROGRAM SARJANA Program Studi Teknik Elektro Sekolah Teknik Elektro dan Informatika I nformatika Silabus dan Satuan Acara Pengajaran (SAP) Kode M atakuli atakuli ah: EL4233
Bobot sks: 3
Semester: 8
KK / U nit Penanggung Jawab:
Sifat:
Sistem Kendali dan Komputer
Wajib
Dasar Sistem dan Kendali Cerdas Nama Matakuliah
Introduction to Intelligent Systems and Control
Silabus Ringkas
Silabus Lengkap
Luar an ( Outcomes) Outcomes)
Intro to Inteligent Systems/Machines and Intelligent Control, Fuzzy Set Theory, Fuzzy rules, Fuzzy Reasoning, Fuzzy Inference Systems, Fuzzy Control, Biological Neural Networks, Neuron Model and Computation, Perceptron, Supervised Learning, Adaptive Linear Networks, Multilayer Feedforward Neural Networks, Networks, BackPropagat BackPropagation, ion, Applications Applications of Intelligent Systems Systems and and Intelligent Intelligent Control, Matlab Implementation, Robotics Intro to Inteligent Systems/Machines and Intelligent Control, Fuzzy Set Theory, Fuzzy rules, Fuzzy Reasoning, Fuzzy Inference Systems, Fuzzy Control, Biological Neural Networks, Neuron Model and Computation, Perceptron, Supervised Learning, Adaptive Linear Networks, Multilayer Feedforward Neural Networks, Networks, BackPropagat BackPropagation, ion, Applications Applications of Intelligent Systems Systems and and Intelligent Intelligent Control, Matlab Implementation, Robotics Intro to Inteligent Systems and Intelligent Control, Characteristics of Intelligent Systems, Fuzzy Set Theory: basic definition and terminology, membership function(MF), fuzzy set theoritic operations, membership function formulation, MF of two dimension, Fuzzy Rules : fuzzy relations, fuzzy relation composition, fuzzy if-then rules, Fuzzy reasoning : compositional rule of inference, fuzzy reasoning, Fuzzy Inference Systems (FIS), Mamdani FIS model, Fuzzy Control : fuzzy control architecture and components, fuzzification, defuzzification, fuzzy rules, fuzzy inference mechanism, fuzzy control structure, fuzzy rules development, fuzzy embedded systems, fuzzy control applications, Biological Neural Networks, Neuron Model and Computation, Artificial Neural Networks (ANN) Topology, Perceptron, Supervised Learning, Perceptron Training, Adaptive Linear Networks, Delta Rule, Multilayer Feedforward Neural Networks (MFNN), MFNN forward computation, MFNN backward computation and Backpropagation, MFNN learning mechanism, ANN application in pattern recognitions and controls, Matlab implementation, Intro to mobile robots as a platform of intelligent systems Intro to Inteligent Systems and Intelligent Control, Characteristics of Intelligent Systems, Fuzzy Set Theory: basic definition and terminology, membership function(MF), fuzzy set theoritic operations, membership function formulation, MF of two dimension, Fuzzy Rules : fuzzy relations, fuzzy relation composition, fuzzy if-then rules, Fuzzy reasoning : compositional rule of inference, fuzzy reasoning, Fuzzy Inference Systems (FIS), Mamdani FIS model, Fuzzy Control : fuzzy control architecture and components, fuzzification, defuzzification, fuzzy rules, fuzzy inference mechanism, fuzzy control structure, fuzzy rules development, fuzzy embedded systems, fuzzy control applications, Biological Neural Networks, Neuron Model and Computation, Artificial Neural Networks (ANN) Topology, Perceptron, Supervised Learning, Perceptron Training, Adaptive Linear Networks, Delta Rule, Multilayer Feedforward Neural Networks (MFNN), MFNN forward computation, MFNN backward computation and Backpropagation, MFNN learning mechanism, ANN application in pattern recognitions and controls, Matlab implementation, Intro to mobile robots as a platform of intelligent systems After completing this course students should able to : Compare crisp set and fuzzy set, Formulate fuzzy membership function, Understand continuous and discrete fuzzy set, Perform various fuzzy set operations, Compute fuzzy relation composition, Compute membership function of fuzzy rules, Understand fuzzy reasoning, Compute Fuzzy Inference System, Design fuzzy logic control, Determize fuzzy rules in fuzzy control, Program fuzzy concepts in Matlab, Understand neuron model, Compute neuron output given an input signal, perform perceptron training, understand adaptive networks, understand supervised learning, comprehend MFNN, perform MFNN forward computation, perform Backpropagation to update MFNN weights, comprehend fuzzy embedded control, program fuzzy control on microprocessor/microcontroller, understand the use of ANN in pattern recognition and in control, compare model based design with intelligent systems methods, use Fuzzy Logic Toolbox in Matlab, use Neural Networks Toolbox in Matlab, implement fuzzy inference system in embedded microcontroller/microprocessor, Understand basic pinciples of of mobile robots robots
M atakuliah atakuliah Terkait Terkait
EL3015 Sistem Kendali EL3014 Sistem Mikroprosesor
Kegiatan Penunjan Penunjan g
Assignment, programming and experimental project
Pustaka
Panduan Penil Penil aian
Prasyarat Prasyarat
Neurofuzz Neurof uzzy y and Sof Softt Com Comput puting ing : A com comput putati ationa onall Appr Approac oach h to to Lear Learnin ning g and and Ma Machi chine ne Int Intell ellige igence nce,, J.S J.S.R .R.. Jang Jang,, C.T. Sun, E. Mizutani, Prentice-Hall, 1997 Fuzzy Control and Identification, J. Lily, 2010 Neural Neu ral Ne Netwo twork rkss : A com compre prehe hensi nsive ve Fo Found undati ation, on, S. Hay Haykin kin,, 2002 2002 Tugas Ujian Tertulis Projek
Bidang Akademik dan Kemahasiswaan ITB Kur2013Teknik Elektro Halaman 1 dari 2 Template Dokumen ini adalah milik Direktorat Pendidikan - ITB Dokumen ini adalah milik Program Studi Teknik Elektro - ITB. Dilarang untuk me-reproduksi dokumen ini tanpa diketahui oleh Dirdik-ITB dan EL-ITB.
Catatan Tambahan
Mg#
Topik
Sub Topik
1
Intro to the course
2
Fuzzy set
3
Fuzzy set operations MF formulation
4
Matlab programming of fuzzy concepts
5
Fuzzy Relation and Fuzzy Rules
6
Fuzzy Reasoning and Its Matlab program
7
Fuzzy Inference System (FIS)
8
9
Fuzzy Control
Fuzzy Control Design and Matlab
10
Fuzzy control design examples and fuzzy embedded control
11
Intro to Mobile robots
Course objective, course syllabus Intro to intelligent systems Characteristic of intelligent systems
Basic definition and terminology Membership function Continuous and Discrete fuzzy set Fuzzy set examples Fuzzy intersection, fuzzy union, fuzzy complement, fuzzy subset MF shape and formulation Matlab code of MF Fuzzy set operation in Matlab Fuzzy relation Fuzzy composition : maxmin composition, max product composition Fuzzy rules Linguistic variables Fuzzy reasoning Matlab code for fuzzy relations, fuzzy rule composition FIS with single antecedent Mamdani FIS with multiple antecedents Fuzzy control architecture Fuzzy control components : fuzzification, defuzzification, fuzzy rules, fuzzy inference Fuzzy rules construction Fuzzy control in Matlab Fuzzy control applications Fuzzy rules examples Fuzzy embedded processor Fuzzy programming Intro to mobile robots Robot sensor Robot control
Capaian Belajar Mahasiswa
12
Biological Neural Networks and neuron Model
13
ANN learning
14
Feedforward Multilayer Neural Networks and Backpropagation
15
ANN training with Backpropagation and Applications
Biological neural networks Neuron model and computation Supervised learning Perceptron model and perceptron learning algorithm Adaptive linear networks Matlab examples MLNN topology MLNN forward computation MLNN backward computation Matlab examples MLNN training ANN applications in pattern recognition and in control
Sumber Materi
Understand basic principles of intelligent system method Compare model based design and intelligent system method
Nurofuzzy and Soft-computing
Understand fuzzy set Characterize fuzzy set using membership function Provide examples of fuzzy set Compare crisp and fuzzy sets
Nurofuzzy and Soft-computing
Perform fuzzy set operations Formulate MF
Neurofuzzy and Soft-computing
Program MF in matlab Program fuzzy set operation in Matlab Understand fuzzy relation and its MF Perform fuzzy composition Determine MF of fuzzy rule Derived composite linguistic values from primary linguistic values
Neurofuzzy and Soft-computing
Neurofuzzy and Soft-computing
Understand fuzzy reasoning Program fuzzy relation, fuzzy rule composition in Matlab
Neurofuzzy and Soft-computing
Compute FIS for single and multiple antecedents Perform graphical representation of FIS with two-inputs and one output
Neurofuzzy and Soft-computing
Comprehend fuzzy control Compute defuzzification
Neurofuzzy and Soft-computing Fuzzy Control and Identification
Develop fuzzy rules based on ideal respons Design fuzzy control using Matlab Design fuzzy control Understand fuzzy embedded processor/controller Fuzzy programming on microcontroller Undersand mobile robot Understand robot sensor Understand robot control Understand basic principles of biological neural networks Comprehend neuron model Compute output of nuron model given input signal
Fuzzy Control and Identification
Fuzzy Control and Identification
Mobile robot
Neural Networks : A Comprehensive Foundation
Understand supervised learning Train perceptron to form classification Comprehend adaptive linear networks and its learning algorithm
Neural Networks : A Comprehensive Foundation
Comprehend MLNN Perform forward computation Perform back-propagation
Neural Networks : A Comprehensive Foundation
Understand ANN training mechanism Understand ANN applications
Neural Networks : A Comprehensive Foundation
Bidang Akademik dan Kemahasiswaan ITB Kur2013-Teknik Elektro Halaman 2 dari 2 Template Dokumen ini adalah milik Direktorat Pendidikan - ITB Dokumen ini adalah milik Program Studi Teknik Elektro - ITB. Dilarang untuk me-reproduksi dokumen ini tanpa diketahui oleh Dirdik-ITB dan EL-ITB.