multilayerperceptron-医学影像处理室mipl-云林科技大学.pptVIP

Chapter 1 Introduction 授課教師: 張傳育 博士 (Chuan-Yu Chang Ph.D.) E-mail: chuanyu@yuntech.edu.tw Tel: (05)5342601 ext. 4337 Office: ES709 What is a Neural Network? A neural network is a massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects: Knowledge is acquire by the network from its environment through a learning process. (learning) Interneuron connection strengths, known as synaptic weights, are used to store the knowledge. (black box) Also referred to as Neurocomputers, connectionist networks, parallel distributed processor. Benefits of Neural Networks The use of neural networks offers the following useful properties and capabilities: Nonlinearity A neuron can be linear or nonlinear Input-Output Mapping Learning with a teacher or supervised learning Adaptivity Neural network adapts their synaptic weights to changes in the surrounding environment. Evidential Response Provide confidence information in decision made Benefits of Neural Networks (cont.) Contextual Information Every neuron in the network is potentially affected by the global activity of all other neurons in the network. Fault Tolerance A neural network exhibits a graceful degradation in performance rather than catastrophic failure. VLSI Implementability The massively parallel nature of a neural network makes it well suited for implementation using VLSI. Uniformity of Analysis and Design The same notation is used in all domains involving the application of neural networks. Neurobiological Analogy The design of a neural network is motivated by analogy with the brain. Human Brain The neural (nerve) net continually receives information, perceives it, and makes appropriate decisions. The receptors convert stimuli from the human body or the external environment into electrical impulses that convey information to the neural net (brain). The effectors converts electrical impulses generated by