Artificial Neural Networks Examination, June 2005 Instructions There are SIXTY questions. (The pass mark is 30 out of 60). For each question, please select a maximum of ONE of the given answers (either A, B, C, D or E).

First Page		Document Content
Date: 2005-06-05 12:55:59 Artificial intelligence Perceptron Artificial neural network Feedforward neural network Multilayer perceptron Backpropagation Generalization error Statistical classification ADALINE Neural networks Cybernetics Science		Artificial Neural Networks Examination, June 2005 Instructions There are SIXTY questions. (The pass mark is 30 out of 60). For each question, please select a maximum of ONE of the given answers (either A, B, C, D or E). Add to Reading List Source URL: aass.oru.se Download Document from Source Website File Size: 160,39 KB Share Document on Facebook

	A Comparison of Tight Generalization Error Bounds Matti K¨ a¨ ari¨ ainen DocID: 1uyBm - View Document
	Margin-based Generalization Error Bounds for Threshold Decision Lists Martin Anthony Department of Mathematics and Centre for Discrete and Applicable Mathematics London School of Economics DocID: 1utHs - View Document
	We show that any model trained by a stochastic gradient method with few iterations has vanishing generalization error. We prove this by showing the method is algorithmically stable in the sense of Bousquet and Elisseeff. DocID: 1sNcs - View Document
	Generalization Error Bounds for the Logical Analysis of Data Martin Anthony Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A2AE, U.K. DocID: 1rUDZ - View Document
	A Few Useful Things to Know about Machine Learning Pedro Domingos Department of Computer Science and Engineering University of Washington Seattle, WA, U.S.A. DocID: 1rgDn - View Document