[SOLVED] CS matlab algorithm Acquired Intelligence & Adaptive Behaviour

Acquired Intelligence & Adaptive Behaviour
Writing a lab report
Christopher L. Buckley

Reports not questions
In each lab you will get question sheet which you should work through
However the portfolio piece will be delivered as a scientific report in the style of a scientific paper.

Resources
Guide to Technical Report Writing
Ten simple rules for structuring papers Brett Mensh and Konrad Kording

Portfolio
Lab report is 8 pages in total (although this first one maybe shorter)
Append your code to the end and put pseudo algorithms in the main text.

Writing a Lab Report
Introduction
Provides background information (e.g., previous studies) and includes the objectives and the hypothesis.
Method
Specifies the details of your study, procedures or related analytic tools. In other words, how did you do it?
Results
Reports the data and analyses based on the data. State whether the results were consistent with the hypotheses, usually without interpretation of any wider meaning or importance. What did you find?
Discussion
Interprets the results of the experiment in terms of wider meaning and importance. What do the results mean?
References
List of works used to write the lab report. http://www.sussex.ac.uk/ei/internal/forstudents/engineeringdesign/studyguides/techreportwriting#1

Introduction
The introduction should be self-contained. Background.
The question.
What you found.

Methods
This gives an overview of how you investigated the questions you motivate in the introduction i.e schematics of the networks and pseudo algorithms.
Imagine someone tried to recreate your work with only your report document and the question sheet alone. Could they do it? If they couldnt then you need to put in some more details.

Results
Present what you found e.g parameters for FBB and time versus stare plots for the RNN

Discussion
A self-critical look at what you have achieved, and what you failed to achieve.
How does it fit with the ideas that you motivated in the introduction

Conclusion
Summarise what you found and describe future work and studies

End matter
Then a bibliography, properly referenced.
And an Appendix with all your code, properly presented and commented.
N.B. remember to spell-check and proof-read!

Portfolio
Technical (20): The quality of your code and the algorithms you present.
Presentation (20): The quality of writing and organisation of the submitted document, the quality of the figures and diagrams.
Context (25): The extent to which you have motivated the work and discussed the results in the context of the ideas presented in the lectures.
Research (35): The extent to which youve gone beyond the lecture material and brought in ideas from the course reading, from other sources and your own ideas.

Required content for portfoio pieces
The required context for each portfolio piece is listed on the Canvas website.
However to get the highest mark you will be expect to have gone beyond this in direction you choose.

The influence of mutation rates on the convergence rate of a GA
Introduction
GAs were developed in 1980s to harness some of this power for optimisation. Here we explore the optimisation capabilities of a simple GA. We show how it can readily evolveS a solution to a simple sorting problem. We demonstrate the dependence of evolutionary convergence on mutation rate. Method
The sample problem was to .. We represented solution to problem as genotype as
The phenotype and fitness were calculated a We implement a simple population based GA, describe the following pseudo code. Mutation was implemented as..,selection was implemented as.. The fitness function was.
Results
Our GA evolved a solution to problem in X generations, see graph. Evolution was rapid over X generations and slower change of Y generation. We changed the mutation rate, fitness function and found. By altering the fitness function we found.
Discussion
Our simple GA readily evolved a solution to the problem. We found the fitness was sensitive to the mutation rate. It the mutation was high then . this is because. We think better performance could be achieved by.
References
List of works used to write the lab report.

Things to remember
No screenshots. Export figures from matlab.
Axes labels.
Think about putting more than one data line on each graph: better for
comparisons.
Make pseudocode short: not full code
Introduction needs to link to what you do in your report