Homework 4


Task 1 (10 pts)

Load the PD N-Person Iterated model in NetLogo. Answer these questions:

  1. Observe the results of running the model with a variety of populations and population sizes. For example, can you get cooperate’s average payoff to be higher than defect’s? Can you get Tit-for-Tat’s average payoff higher than cooperate’s? What do these experiments suggest about an optimal strategy? (2-3 sentences)
  2. Relate your observations from this model to real life events. Where might you find yourself in a similar situation? How might the knowledge obtained from the model influence your actions in such a situation? Why? (3-4 sentences)

Task 2 (20 pts)

Read/skim “Strong and Weak Emergence” by David Chalmers from 2006 (PDF; full citation). Answer these questions:

  1. Chalmers writes, “We can think of strongly emergent phenomena as being systematically determined by low-level facts without being deducible from those facts.” Give an example (1-2 sentences) that may possibly satisfy this definition of strong emergence.
  2. Are the NetLogo models we have been using examples of strong or weak emergence? Provide a 1-2 sentence argument.
  3. What is the relation between weak emergence, as described by Chalmers (second half of the reading) and the knowledge level? This is a “compare and contrast” type of question. Answer in one paragraph (4-5 sentences).

Task 3 (20 pts)

Execute the k-means algorithm by hand on the following data:

item #wxyztrue label

Use \(k=2\). Show the centroids as they change, and give the final centroids. You must choose random (or not so random) starting centroid values. Finally, give the confusion matrix.

Task 4 (10 pts)

Run the k-means algorithm in Weka using this dataset: iris.arff (iris species clustering).

Find the best value of \(k\). Give the confusion matrix for this \(k\). Also report the percent of correctly classified instances for each class.

Task 5 (20 pts)

Execute the k-nearest neighbor algorithm by hand on the clusters found from task 1 (or make up random clusters by labeling the points from task 1). Use \(k = 2\). Classify the data point: \(<1, 0, 1, 2>\).

Task 6 (10 pts)

Run the k-nearest neighbor in Weka using this dataset: letter.arff (handwritten letter classification). Find the best value of \(k\). Report the accuracy and give the confusion matrix.

Task 7 (10 pts)

Explain the differences between k-means and k-nearest neighbor algorithms. What does each accomplish, and when/why might you use both?

Extra credit (20 pts)

Play around with Weka. Report how well at least three different classification algorithms (avoid k-means and k-nn) perform on the the letter.arff data. Collect accuracies in a table.

AI Su13 material by Joshua Eckroth is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License. Source code for this website available at GitHub.