School of Enginering
UCLan Coursework Assessment Brief
|Module Title: Machine Intelligence
Module Code: EL3300
|Experimental Design and Investigation of Optimisation Algorithms||This assessment is worth 50% of the overall module mark|
The following Learning outcomes will be assessed in this assessment
· Develop simple representations and simulations of machine learning processes using appropriate mathematical descriptions and software based simulations.
Introduction and background
This assignment will demonstrate your ability to design and carry out an experiment based on engineering principles, write software and report your finding.
In the lectures we have looked at a number of optimisation algorithms.
In order to test the optimisation algorithms a fitness function is required, a library (Windows dll) is available on blackboard that will return a grading value for any run given to it. (See Appendix A on how to reference and use the library in Visual Studio for a C# application.)
A run would consist of a 100 character long binary string representing 100 binary inputs, after submitting this to the library the library will return an integer. The bigger the integer score the more successful the configuration (the maximum return is unknown to the student), if the library is presented with a string of a different length than 100 it will return a score of -99999.
It is the student’s task to initially select one of the algorithms studied in the lectures that is suitable for this task and write a C# program to implement the algorithm using the fitness function library. Once this has been accomplished the task should be repeated for at least one of the other algorithms and the results compared. Experiments using the algorithms should be conducted in a logical manner suitable for an engineering task (logical handling and testing of algorithm parameters).
N.B. This assessment can be passed by implementing a single algorithm well but in order to achieve a 1st class mark a student must implement at least two and compare the results (although this will not guarantee a 1st class grade).
All code should be properly commented.
The report and software projects should be zipped into a single file and submitted to Blackboard.
· A report detailing algorithm implementation, results, comparisons and conclusions (report length should not exceed 2000 words)
· A standard UCLan coursework coversheet.
· All software code.
Notes on the report.
The report should consist solely of details of the software implementation, the results, comparisons and conclusions. Do not spend time (and words) explaining the details of how the algorithms work (this was covered in the lecture slides).
Notes on the program(s).
It is anticipated that the student will write the program using C# in Visual Studio and example and explanations of how to use a dll in that environment are provided. If the student wishes to use any variation from this then they should contact the lecturer beforehand and gain approval (for example implementation in C/C++ would also be acceptable). If the student chooses to use a language or IDE different from those mentioned here it is their responsibility to ensure they can call the fitness function dll. The student should write the algorithm code rather than use a third party library (such as Accord). In terms of the different algorithms the student is free to write a single program or different programs for each algorithm (all code must be submitted). The user interface for the program is entirely up to the student, the assessment is based only on the implementation of the algorithms not the usage of the programs (it is the student that will be using the program).
|PREPARATION FOR THE ASSESSMENT
|RELEASE DATES AND HAND IN DEADLINE
Assessment Release date: 11th Feb 2021 Assessment Deadline Date: 11.59pm 18th April 2021
Your feedback and mark for this assessment will be provided within the University’s 15 working day policy for feedback. Written feedback will be available on Blackboard on or before 3/5/21.
Submit a single zip file containing the report and all software written to the Turnitin page on Blackboard.
HELP AND SUPPORT
· Support for the assessment is provided in the lab sessions. Additional support can be provided by booking a session with the module team via MSTeams/drop in when available.
· For support with using library resources, please contact Bob Frost email@example.com or SubjectLibrarians@uclan.ac.uk. You will find links to lots of useful resources in the My Library tab on Blackboard.
· If you have not yet made the university aware of any disability, specific learning difficulty, long-term health or mental health condition, please complete a Disclosure Form. The Inclusive Support team will then contact to discuss reasonable adjustments and support relating to any disability. For more information, visit the Inclusive Support site.
· To access mental health and wellbeing support, please complete our online referral form. Alternatively, you can email firstname.lastname@example.org, call 01772 893020 or visit our UCLan Wellbeing Service pages for more information.
· If you have any other query or require further support you can contact The <i>, The Student Information and Support Centre. Speak with us for advice on accessing all the University services as well as the Library services. Whatever your query, our expert staff will be able to help and support you. For more information , how to contact us and our opening hours visit Student Information and Support Centre.
· If you have any valid mitigating circumstances that mean you cannot meet an assessment submission deadline and you wish to request an extension, you will need to apply online prior to the deadline.
|Disclaimer: The information provided in this assessment brief is correct at time of publication. In the unlikely event that any changes are deemed necessary, they will be communicated clearly via e-mail and a new version of this assessment brief will be circulated.||Version: 1.1|