CS 5073 Take Home Exam

Due 11:59 pm, Thursday, 14 April 2022

1. Motivation

To test your understanding of artificial neural networks (ANNs), evolutionary computation (EC), and neuroevolution, this exam requires you to design a neuroevolutionary system and experimental setup that, if implemented, could be used to study an interesting set of research questions related to topics we have covered in this class. You will need to think carefully about the interrelationships of ANN and EC design, as well as experimental design in general, in designing this neuroevolutionary system.

2. Goal

The goal of this assignment is to test your understanding of course concepts by requiring you to apply them to an authentic neuroevolutionary problem.

3. Assignment

Design a neuroevolutionary system and associated experimental setup to use for studying the following. Be sure to specify and justify all aspects of this system and setup. Write up your design in the form (length, tone, content, etc.) of an experimental design section of a research paper.

Note that this design should be sufficiently detailed such that any person who is proficient in the relevant topics (neuroevolution and software development) could implement code to carry out the neuroevolutionary experiments you describe and get results that are highly likely to be in accordance with the results that would be obtained by any other person who is also proficient in the relevant topics who independently implemented code to carry out the experiments you describe. That is, you do not need to explain neuroevolution or software development in your description. However, all of the particulars of your design necessary to carry out the experiments and arrive at the results should be given.

Note also that you will not actually implement this design nor carry out the experiments. You will only be designing and writing up the system and the experiments which someone could carry out. You will not include a results section because you will have no results to report but you should explain the types of data that would be collected, if someone were to carry out these experiments, and how that data would be analyzed.

Problem Description

Prof H wants to develop ANNs capable of effective categorization within datasets of complex data for which spatial relationships are key to success. Examples of such datasets in two dimensions include images, in which the spatial relationships of pixel values are key to image classification, and Go (or Weiqi), in which the spatial arrangements of playing pieces on the board are key to recognizing patterns that may be associated with particular tactics. He's also interested in application domains with more than two spatial dimensions, as well as those with just one spatial dimension.

Rather than designing different ANNs for different datasets, Prof H would like to use a neuroevolutionary system to evolve an appropriate ANN for each dataset. He would like there to be a high degree of flexibility in the possible neural architectures evolved and, if possible, he would like to see multiple, very different architectures evolved for the same task. He also thinks that allowing for customized weight-update mechanisms (e.g., learning rules) might allow for more effective ANNs to evolve, that both topological symmetries and asymmetries might be highly useful for different parts of the system, and that environments can have a drastic effect on evolutionary outcomes.

Prof H also thinks that what constitutes effective classification should be left to the user of this neuroevolutionary system. That is, for a straightforward image classification system, classification accuracy might be considered the appropriate measure of effectiveness, whereas for a Go-playing system, game performance (e.g., winning more games or scoring more points) might be used instead. That is, for the Go-playing system, there may be no predefined patterns (classes) for the system to learn—instead, it should learn whatever patterns lead to good game performance.

In designing your neuroevolutionary system and associated experiments, here are some questions to consider:

Note that you do not have to consider all or even many possible neuroevolutionary designs and/or experiments appropriate to explore these ideas. A single system and a single experiment is sufficient.

5. What to Turn In

You will turn in to the appropriate drop box in Canvas a machine readable electronic copy of your work that completes the exercise above.