skip to Main Content
The smarter way
to do assignments.

Please note that this is just a preview of a school assignment posted on our website by one of our clients. If you need assistance with this question too, please click on the Order button at the bottom of the page to get started.

I need support with this Machine Learning question so I can learn better.Objective: Comparing and analyzing various machine learning algorithms acrossvarious data sets using Weka open source. Both supervised and unsupervisedapproaches will be looked at in this assignment.NOTE: Programming is not required for this work if using WEKA, hence put youreffort in the analysis and report. Be sure to include any references you use for thereport. Setting up WEKA should take less than an hour. The run times for thesealgorithms should be very short, all take seconds for a single run, except for theneural network that takes a few minutes. You need to use multiple runs for yourreport— (Use the experimenter feature described at the tutorial how to setmultiple runs in WEKA).Part A: Supervised LearningYou are to compare three popular supervised learning algorithms across fourclassification data sets.Decision tree: Algorithm 1 will be a C4.5 decision tree. This algorithm can befound in Weka under the classify tab using the label trees/J48.Neural network: Algorithm 2 will be a standard neural network trained using backpropagation. This algorithm can be found in Weka under the classify tab using thelabel functions/MultilayerPerceptron.K nearest neighbours: Algorithm 3 will be using the K nearest neighboursclassification algorithm (will be reviewed on Tuesday tutorial, however,you c).This algorithm can be found in Weka under the classify tab using the labellazy/IBk.Data sets:Iris classification data setContains features regarding iris plants, with the goal of determining whichclass of iris the plant is.There are 150 input vectors. Each input vector contains 4 attributes, and 3possible classifications.https://archive.ics.uci.edu/ml/datasets/IrisWisconsin breast cancer data setContains medical features of a tumour, with the goal of determining if thetumour is malignant or benign.There are 699 input vectors. Each input vector contains 9 attributes, and 2possible classifications.https://archive.ics.uci.edu/ml/datasets/Breast+Can…inal%29Car evaluation data setContains features regarding different vehicles, with the goal of determiningthe safety level of the car.There are 1728 input vectors. Each input vector contains 6 attributes, and 4possible classifications.https://archive.ics.uci.edu/ml/datasets/Car+Evalua…Diabetic retinopathy data setContains features of medical images, with the goal of determining whetherthe image shows signs of diabetic retinopathy or not.There are 1151 input vectors. Each input vector contains 20 attributes, and2 possible classifications.https://archive.ics.uci.edu/ml/datasets/Diabetic+R…ata+SetFor part A, analyze the performance of each required algorithm for each data set.What observations can you make regarding the data set used and the modelstrained? Does one approach beat all others for every data set, or do differentapproaches work better on the different problems? Using your understanding ofthe algorithms, try and explain the observations you make. Try modifying theparameters for the different algorithms. Does changing the parameters from theirdefault values significantly impact the performance of the algorithm?Part B:Implement and analyze the performance of clustering on unsupervised data setsusing various clustering algorithms. For this part you will use the K-meansclustering algorithm. The data sets that you will use are available at the followinglink: http://cs.joensuu.fi/sipu/datasets/Note: Use the S1, S2, S3 and S4 data sets. Feel free to use any additionaldata sets from the above link. The data sets will need to be converted into an arfffile as explained in tutorial for use with Weka.You are to make observations regarding how the k-means clustering works on thedifferent data sets. How does modifying the number of clusters impact the withincluster sum of squared error? What happens if you use too many or too fewclusters? What sort of impact would you expect from modifying the way clustersare initialized? What observations can you make comparing the clustering on aneasily separable data set (s1) to one where the optimal clusters are a lot less clear(s4)?For bonus marks, extend your analysis by including a self-organizing mapapproach (self-organizing maps is not a topic typically covered in 4P76 but it is aseminar topic that will be presented and is worth knowing). To install the selforganizing map package, on the Weka home page select the tools tab and click onpackage manager. In the package manager, select the SelfOrganizingMap packageand click install. It will now be available under the cluster tab. Compare the selforganizing map clustering approach to the k-means clustering approach. Howdoes its clustering procedure differ from that of k-means? What sort of impactdoes modifying the lattice width and height have on the algorithm? Whatobservations can you make when the values are the same, or when one value islarger then the other?Assignment Requirements and Grading: The results are to be handed in via atechnical paper written in the IEEE format shown to you in tutorial. Your reportshould contain the following headers and sections:Abstract, Introduction & problem definitionWhat is the goal of this work? Outline of the rest of the paper, etc.
Clear definition of the problem and data sets being used, summary of
supervised and unsupervised learning, applicability of the two approaches.BackgroundYour background section will contain two subsections, one on supervised
learning and one on unsupervised learning.Describe the basics of each included algorithm, including relevant formulas
and equations.Descriptions should include a bit about the different parameters, but since
they are not the focus of this assignment you do not need as much detail.Results and DiscussionThis section will also be split into two subsections, one for supervised
learning and one for unsupervised learning.This section will include all the observations you made, as well as
experimental evidence to support your claims.Be sure to include figures and plots that will enhance your observations and
provide further supporting evidence to your claims.ConclusionsBriefly summarize all that was done in your paper.
Include a summary of the experiments done and the conclusions you made
in your results section. Requirements: 3 pages

GET HELP WITH THIS ASSIGNMENT TODAY

Clicking on this button will take you to our custom assignment page. Here you can fill out all the additional details for this particular paper (grading rubric, academic style, number of sources etc), after which your paper will get assigned to a course-specific writer. If you have any issues/concerns, please don't hesitate to contact our live support team or email us right away.

How It Works        |        About Us       |       Contact Us

© 2018 | Intelli Essays Homework Service®

Back To Top