智能系统chap1.ppt

jkim@cs.kaist.ac.kr 智 能 系 统 (NC + EC + PCA + ML) Lecture Note Zhao Jie Yu Computer Science Department Ningbo University Part 1. Neural Computation What is an Artificial Neural Network ? Computational model inspired from neurological model of brain Human brain computes in different way from digital computer(the von Neumann machine) highly complex, nonlinear, and parallel computing many times faster than d-computer in pattern recognition, perception, motor control has great structure and ability to build up its own rules by experience dramatic development within 2 years after birth continues to develop afterward Language Learning Device before 13 years old Plasticity : ability to adapt to its environment The most important: it is alive! Neural Network Definitions Machine designed to model the way in which brain performs tasks implemented by electronic devices and/or software (simulation) Learning is the major emphasis of NN Massively parallel distributed processor massive interconnection of simple processing units simple processing units store experience and make it available to use knowledge is acquired from environment thru learning process Learning Machine modify synaptic weights to obtain design objective modify own topology - neurons die and new one can grow Connectionist network - connectionism Benefits of Neural Networks(I) Power comes from massively parallel distributed structure and learn to generalize generalization : ability to produce reasonable output for inputs not encountered during training NN cannot provide solution by working individually Complex problem is decomposed into simple tasks, and each task is assigned to a NN Long way to go to build a computer that mimic human brain 1. Non-linearity interconnection of non-linear neurons is itself non-linear desirable property if underlying physical mechanism is non-linear Benefits of Neural Networks(II) 2. Input-Output Mapping input-output mapping is built by learning from examples reduce differen