Assignments


 * HW # 1 **
 * Part 1 ( Due on March 1 )**

Using the function provided in Unit # 2, compare the performance of different combination of selection schemes in an EA. The following schemes should be considered: Parent Selection: Fitness Proportional, Rank-based and Binary Tournament Survival Selection: Truncation and Binary Tournament

Each combination should be run at least 10 times and the evaluation should be performed using: (i) average best-so-far curve and (ii) average average-population fitness curve

You will present your findings in the class. You are welcome to try your own ideas as well in addition to the tasks described above.

Compare the two combinations of your choice (found in Part 1) against canonical versions of Evolutionary Programming and Evolutionary Strategies. For Evolutionary Strategies, use both (1 + lambda) and (mu + lambda) version.
 * Part # 2** **( Due on March 15 )**

Keep the population size as 10 for all the algorithms (except for 1+lambda ES).

For this part, use the Rosenbrock function provided in Unit # 3.


 * Part # 3** **( Due on March 22 )**

Solve TSP using the following algorithms:

(i) Ant Colony Optimization (ii) An Evolutionary Algorithm with "generational scheme" (iii) An Evolutionary Algorithm with your favorite combination of parent/survival selection

Use the Qatar and Uruguay data sets available on the following link to test your algorithms http://www.tsp.gatech.edu/ world/countries.html

Discuss your findings in the class

**HW # 2** ( ** Due on April 15 ** )

Present a topic related to Computational Intelligence that is not covered in the given syllabus.

HW # 3

Implementation of backpropagation algorithm and a hybrid EA/PSO-NN.

Project

Presentation + Implementation