Sistem Kecerdasan Buatan RAHMAT FAUZI , S.T. M.T

Objective To have an understanding of artificial neural networks (ANNs), fuzzy systems, and evolutionary algorithms; and their application intelligent systems. To have a capability in realizing an intelligent system consists of the ANN, fuzzy system, and evolutionary algorithm (programming skill).

content • Artificial Neural Networks • Fuzzy Systems • Evolutionary Algorithm • Special topics of intelligent systems

reference Principles of neurocomputing for science & engineering, Fredric M Hum, Ivica Kostanic, McGraw-Hill Inc., 2001 Neuro-fuzzy and soft computing, JSR Jang, CT Tsun, E. Mizutani, Prentice Hall Inc., 1997. Neural network fundamental, NK Bose and P. Liang, McGraw Hill, 1996. Evolutionary Computation, David B Fogel, IEEE Press. Fuzzy logic and intelligent systems, Hua Li, M Gupta (Eds), Kluwer AcPress, 1995. Fundamentals of the new artificial intelligence: beyond traditional paradigm, Springer-Verlag, 1998. Ahmad Arifin, Presentation Material. ITS. 2011.

Intelligence means… The ability to solve hard problem (Minsky). Capability to learn to perform various function within a changing environment to survive and to prosper (Carne). Property in which the organism senses, reacts, learns from, and subsequently adapts its behavior to its present environment in order to better promote its own survival (Atmar) Capability of a system to adapt its behavior to meet its goals in a range of environments (Fogel)

From Conventional AI to Computational Intelligence An advance computer technology which is concerned with making machines work in intelligent way, mimicking the way of human mind. Conventional AI: physical symbol system hypothesis.

Expert System (most successful conventional AI)

Intelligent System Scheme Methodology Strength Neural Network Learning and Adaptation Fuzzy Set Theory Knowledge representation via fuzzy if-then rules Genetic Algroithm and simulated annealing Systematic random search

Artificial Neural Network

Basics of Neuroscience and Neuron Models ANNs (also called parallel distributed processing systems) and connectionist systems are intended for modeling the organizational principles of the central nervous system. Biologically inspired computing capabilities of ANN is expected to allow the cognitive and sensory task to be performed more easily

NERVOUS SYSTEM

Basics of Neuroscience Human nervous system is made up of a vast network of computing elements (neurons) with brain as a central unit. The brain is connected to receptors that bring sensory information, and it delivers command to effectors. A biological neuron consists three main components: dendrite, cell body, and axon. Function of nervous system is represented by activities of neurons, topology of the connections, and theirstrength.