MFA501 Mathematical Foundations of AI April 26, 2021 postadmin Post in Uncategorized MFA501 Assessment 2 Brief Problem Sets Modules 6, 10 Page 1 of 5Task SummaryIn this assessment, you will be given a wide range of programming exercises to complete, whichrequire using and applying mathematical concepts. These will be submitted in Module 6 (20%) and inModule 10 (20%). This assessment is to be completed individually and you are to submit a zip fileincluding source code, debug, and release build and supporting documents for each problem set.ContextThis assessment activity assesses your skills in employing AI mathematical foundation to solve realworld problems and scenarios. The assessment is made of two parts due in modules 6 and 10 overthe course of trimester.Task Instructions The programs that you submit should be free of warnings and errors. You need to submit the source code and the executable format.o Name the source code folder as:MFA501_Assessment2_Week6_LastName_FirstName.zipo MFA501_Assessment2_Week10_LastName_FirstName.zip Your code should be structured and written with the best practices in the field ofprogramming. There should be enough number of comments in the source files to show yourunderstanding of the program. Any third-part code should be appropriately attributed. ASSESSMENT 2: PROBLEM SETS BRIEFSubject Code and TitleMFA501 Mathematical Foundations of AIAssessmentProblem SetsIndividual/GroupIndividualLengthLearning OutcomesThis assessment addresses the Subject Learning Outcomes outlinedat the bottom of this document.SubmissionDue by 11:55pm AEST Sunday end of: Module 6 (Week 6) (20%) Module 10 (Week 10) (20%)Weighting40%Total Marks100 marks MFA501 Assessment 2 Brief Problem Sets Modules 6, 10 Page 2 of 5After implementation and testing your programs, write a reflective report detailing the experienceof the development process. The report needs to be at least 500 words in length and include thefollowing sections: Overview Justifications and elaborations on the mathematical approaches and models used to solvethe cases study Justifications and elaborations on the programing methods and practices used to implementthe mathematical approaches and models What went right What went wrong What you are not sure about ConclusionYour problem sets should include the following elements and should be zipped prior to submission: Release Build Zip: A release build executable must be zipped and included with thesubmission. Ensure that project settings are set to Release when creating this build. Source Code Zip: All relevant source code files and project files must be zipped and includedwith the submission Reflective report: PDF or Word Naming & File structure for the zip file (should be done for all problem sets) .o MFA501_Assessment2_Set1_Release Build_LastName_FirstName.zipo MFA501_Assessment2_Set1_Source_LastName_FirstName.zipo MFA501_Assessment2_Set1_report_LastName_Firstname.pdf or .docx Make sure to submit Problem Set 1 by Sunday 11:55pm Module 6 Make sure to submit Problem Set 2 by Sunday 11:55pm Module 10Submission InstructionsThis assessment task is due in two stages throughout the trimester as outlined above. Please submityour completed assessments via the Assessment link in the main navigation menu in MFA501Mathematical Foundations of AI. The Learning Facilitator will provide feedback via the Grade Centreon Blackboard. Feedback can be viewed in My GradesMFA501 Assessment 2 Brief Problem Sets Modules 6, 10 Page 3 of 5Assessment 2 Rubric AssessmentAttributesFail(Yet to achieveminimum standard)0-49%Pass(Functional)50-64%Credit(Proficient)65-74%Distinction(Advanced)75-84%High Distinction(Exceptional)85-100%Work demonstrates theknowledge andunderstanding of linearalgebra in AI20%Little or no knowledge oflinear algebra in AI.The calculations and codesare mostly incorrect.Acceptable but further work isrequired to show theknowledge of linear algebra inAI. The calculations and codesare mostly correct withoccasional inaccuracies anderrors.Good level of knowledgeabout linear algebra in AI.The calculations and codesare correct with no errors.The codes are not efficientfor the case study.Very good but not thoroughknowledge about linearalgebra in AI. Thecalculations and codes areaccurate. The codes areoccasionally not efficient.Excellent and thoroughunderstanding of linearalgebra in AI. Thecalculations and codes areaccurate and completelyerror-free. The mostefficient implementationsare given.Work demonstrates theknowledge andunderstanding ofcalculus in AI20%Little or no knowledge ofcalculus in AI.The calculations and codesare mostly incorrect.Acceptable but further work isrequired to show theknowledge of calculus in AI.The calculations and codesare mostly correct withoccasional inaccuracies anderrors.Good level of knowledgeabout calculus in AI. Thecalculations and codes arecorrect with no errors. Thecodes are not efficient forthe case study.Very good but not thoroughknowledge about calculus inAI. The calculations andcodes are accurate. Thecodes are occasionally notefficient.Excellent and thoroughunderstanding of calculusin AI. The calculations andcodes are accurate andcompletely error-free. Themost efficientimplementations are given.Work demonstrates theknowledge andunderstanding ofprobability in AI20%Little or no knowledge ofprobability in AI.The calculations and codesare mostly incorrect.Acceptable but further work isrequired to show theknowledge of probability inAI. The calculations and codesare mostly correct withoccasional inaccuracies anderrors.Good level of knowledgeabout probability in AI. Thecalculations and codes arecorrect with no errors. Thecodes are not efficient forthe case study.Very good but not thoroughknowledge about probabilityin AI. The calculations andcodes are accurate. Thecodes are occasionally notefficient.Excellent and thoroughunderstanding ofprobability in AI. Thecalculations and codes areaccurate and completelyerror-free. The mostefficient implementationsare given.Work demonstrates theknowledge andunderstanding ofstatistics in AILittle or no knowledge ofstatistics in AI.The calculations and codesare mostly incorrect.Acceptable but further work isrequired to show theknowledge of statistics in AI.The calculations and codesare mostly correct withGood level of knowledgeabout statistics in AI. Thecalculations and codes arecorrect with no errors. Thecodes are not efficient forVery good but not thoroughknowledge about statisticsin AI. The calculations andcodes are accurate. Thecodes are occasionally notExcellent and thoroughunderstanding of statisticsin AI. The calculations andcodes are accurate andcompletely error-free. The MFA501 Assessment 2 Brief Problem Sets Modules 6, 10 Page 4 of 5 20%occasional inaccuracies anderrors.the case study.efficient.most efficientimplementations are givenThe reflective essaydemonstrates theknowledge andunderstanding of thewhole process ofimplementing and usingthe mathematicalmodels and methods tosolve the case study.20%The reflective essayincludes no or littlesections and conceptsrequired. There is no orlittle elaborations orjustifications on the use ofthe mathematical modelsand methods used to solvethe case study.The reflective essay includessome of the sections andconcepts required. There islittle elaborations orjustifications to demonstratethe knowledge andunderstanding of the wholeprocess of implementing andusing the mathematicalmodels and methods to solvethe case study.The reflective essay includesall the sections andconcepts required.Elaborations andjustifications are notdiscussed well to show theknowledge and thoroughunderstanding of the wholeprocess of implementingand using the mathematicalmodels and methods tosolve the case study.The reflective essay includesall the sections andconcepts required.Elaborations andjustifications are notthorough and in-depth todemonstrate mastery of thewhole process ofimplementing and using themathematical models andmethods to solve the casestudy.The reflective essay includesall the sections andconcepts required.Elaborations andjustifications are thoroughand show the mastery ofthe whole process ofimplementing and using themathematical models andmethods to solve the casestudy. The following Subject Learning Outcomes are addressed in this assessmentSLO a)Formulate key mathematical concepts used in Artificial Intelligence.SLO b)Apply mathematical techniques in manipulating large data sets, and in designing and analysing experimental work in AI.SLO c)Use standard mathematical notations and terminologies in statistics, probabilities, linear algebra, vectors, matrixes, differential calculus,and logical reasoning.SLO d)Compute accurately standard computations in statistics, probabilities, linear algebra, vectors, matrixes and differential calculus. MFA501 Assessment 2 Brief Problem Sets Modules 6, 10 Page 5 of 5