文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 外语学习 > 英语学习 > COMP3308_Introduction to Artifical Intelligence_2014 Semester 1_Tutorial_w8
侵权投诉

COMP3308_Introduction to Artifical Intelligence_2014 Semester 1_Tutorial_w8

University of Sydney_COMP3308_Introduction to Artifical Intelligence_2014 Semester 1

COMP3308_Introduction to Artifical Intelligence_2014 Semester 1_Tutorial_w8

COMP3308/3608 Artificial Intelligence, s1 2014

COMP3308/3608 Artificial Intelligence

Week 8 Tutorial exercises

Backpropagation Neural Networks

This week we have a smaller number of tutorial exercises. We will use the remaining time for questions about the assignment and covering of additional material:

COMP3308 students: we have reserved the remaining tutorial time for questions about

Assignment 1. Prepare your questions in advance and ask your tutor!

COMP3608 students: we will use the remaining tutorial time to cover an additional topic

“Ensembles of classifiers”.

a) Show that the derivative for the hyperbolic tangent sigmoid

is 1-a2.

b) Write the weight change rule for the hyperbolic sigmoid transfer function, using the result from a). See slide 26 from the lecture.

for an output neuron i:

wji

for a hidden neuron j:

wkj

a) A 2-layer feed-forward neural network with 10 input units, 5 hidden units and 3 output units contains how many weights? (Include biases.) Show your work.

b) The backpropagation algorithm iterates until it minimizes what?

c) Is the backpropagation algorithm guaranteed to achieve 100% correct classification for any linearly-separable set of training examples, given a sufficiently small learning rate? Explain briefly.

Cybenko’s theorem (slide 39) states that any continuous function can be approximated by a backpropagation network with 1 hidden layer. Why do we use networks with more than 1 hidden layer?

1. Load the iris data (iris.arff). Choose 10-fold cross validation. Run the Naïve Bayes and Multilayer percepton (trained with the backpropagation algorithm) classifiers with the default parameters and compare their performance. Note that multilayer perceptron in Weka is under “Functions”.

Which classifier was more accurate? Which one learned faster?

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email