lec03神经元ece cs me539人工神经网络模糊系统简介.pdf

Outline • What is an Artificial Neura work (ANN)? • Basic Definitions: – Neuron functions • Activation functions – ANN Configurations • What is Learning? • Supervised Learning and Function Approximation • Bias and Variance Trade-offs • Model Selection and Sampling Strategy (C) 2010 - 2016 by Yu Hen Hu 2 What is an Artificial Neura work? • Neura works ar works of neurons, for example, as found in real (i.e. biological) brains • Artificial neurons are crude approximations of the neurons found in real brains. They may be physical devices, or purely mathematical constructs. • Artificial Neura works (ANNs) ar works of Artificial Neurons and hence constitute crude approximations to parts of real rains. They maybe physical devices, or simulated on conventional computers. • From a practical point of view, an ANN is just a parallel computational system consisting of many simple processing elements connected together in a specific way in order to perform a particular task • One should never lose sight of how crude the approximations are, and how over-simplified our ANNs are compared to real brains. (C) 2010 - 2016 by Yu Hen Hu 3 The Nervous System • The human nervous system can be broken down into three stages that can be represented in block diagram form as (Arbib, 1987) • The receptors convert stimuli from the external environment into electrical impulses that convey information to the neura (brain) • The effectors conver ectrical impulses generated by the neura into responses as