KF7006 Machine LearningAssignment B – (60% of module mark)COURSEWORK ASSESSMENT SPECIFICATIONDates and Mechanisms for Assessment Submission and Feedback Module Title:Machine LearningModule Number:KV7006Module Tutor Name(s):Dr. Ossama AlshabrawyAcademic Year:2020-2021– SemesterTwo%Weighting:This assignment accounts for60% of the total mark of the moduleCoursework Title:AssignmentB – TheDesign,Development, Analysisand PerformanceEvaluationof Deep Learning algorithmsWord LimitThe word limit for the report is1600-2000 words, not including thefront cover,table ofcontents page, references and appendices. Date of Handout to Students:15th February 2021Date andTime of Submission by Student:25th May 2021 (by 11:59 pm)Mechanism for Submission ofAssessment:The report should be submitted through Turnitin via Blackboard. The submitted files should bezipped in one file (.zip) including the report and the pythoncode files. It is your responsibility toensure that your assignment arrives before the submission deadline stated above. See theUniversity policy on late submission of work.Date by which Work, Feedback and Marks will be returned to Students:23th June 2021 (20 working days)Mechanism for return of assignment work, feedback and marks to students:Feedback and marks on ELP (Blackboard collaborate). Learning Outcomes tested in this assessment (from the Module Descriptor):Knowledge & Understanding:• Demonstrate knowledge and understanding of the core concepts of machine learning andits underlying mathematical foundations• Demonstrate knowledge and understanding of the principal advanced machine learningtechniques for solving real world problems.Intellectual / Professional skills & abilities:• Critically evaluate machine learning algorithms and applications.• Analyse, design and develop machine learning solutions and evaluate their performanceNature of the submission required:All the work for this assessment should be produced as a word (.docx) or PDF document (.pdf) forthe report plus a single zipped file (.zip) of the code. This report will be then submitted to Turnitinand the code will be submitted directly to Blackboard. Both of the report and code should identifythe student by name and ID.Instructions to students:This is an individual work and you CANNOT work with others to construct your work. During thesemester there are numerous opportunities to seek and get advice and support on your work, fromtutors and peers but you must ensure you do not do work for others or copy work from others.Academic Conduct:You must adhere to Northumbria University regulations on academic conduct. AssessmentRegulations for Taught Awards (ARTA) contain the regulations and procedures applying tocheating, plagiarism and other forms of academic misconduct. The full policy is available on theUniversity website. You are reminded that plagiarism, collusion and other forms of academicmisconduct as referred to in the Academic Misconduct procedure of the assessment regulations aretaken very seriously. Assignments in which evidence of plagiarism or other forms of academicmisconduct is found may receive a mark of zero.If you need an extension:Contact ask4Help. Tutors and Module tutors cannot change deadlines.Disabled studentsContact the module lead tutor about reasonable adjustments.Submission RequirementsYou must comply to the following criteria to fulfil the assignment submission requirements:o The word limit is 2000. However, if the assignment is within +10% (i.e., up to 200words) then NO penalty will be applied.o The word count should be declared on the cover page of your assignment. The wordcount does not include title page, table of contents page, references and appendices.Please note, in text citations [e.g. (O’Brien, 2020)].Late submission of work• If you submit up to 1 working day (24 hours), then 10% of the total marks will bededucted.• If you submit the assignment more than 1 working day (24 hours) after the deadlinewithout approval, a mark of ZERO will be awarded for the assignment.Assessment BriefLately, deep Learning has a tremendous amount of attention especially in medical image analysis. Inthis assignment you will be required to design, develop, analyse and evaluate an appropriate deeplearning model. You can build your own model or use a pretrained model with your layers added toit. You will explore the dataset and then apply that model to a dataset of your choosing. You willneed to evaluate the performance in terms of precision, recall, F1-score, ROC-curve and PR-curve.You will discuss the findings that have been produced, and critically reflect upon the model and itspredictions.Assessment Tasks:You have been provided with access to three datasets; all are available on Kaggle (Please see linksbelow). The data covers the following scenarios:• Classification of blood cell types• Chest X-ray classification to COVID-19, Viral Pneumonia, normal• Brain tumour detection from MRI imagesYou are required to choose one of the above scenarios as your assignment. Your task is to produce adeep learning model that is appropriate to the problem. The model can be your own model ordesigned based on fine-tuning of a pretrained model. You are required to conduct datapreparation/transformation to make the data ready for the model. Please note that what will beprovided in the report should reflect on the python code. Please also note NOT to take on anyexisting code online as your own work. The errors in the code will affect your mark final mark.The key components you must complete are:1. Explore the dataset to understand its characteristics [10 Marks]2. Pre-process your data to be suitable for building the model [10 Marks]3. Build the model that allows for the task specified for chosen dataset [20 Marks]4. Evaluate the model predictions using the metrics stated above. [15 Marks]5. Fine-tune the model to get better predictions on the test set [15 Marks]6. Present your findings with suitable visualisations that are easy to interpret [15 Marks]7. Critically evaluate and discuss the whole process and he findings and what can be improved[15 Marks]Please note: to ensure fairness across the different datasets/research questions, the actual performance (e.g.measured through metrics such as accuracy) of your model will not contribute towards the mark that is received.Datasets:1. Blood cells images dataset: https://www.kaggle.com/paultimothymooney/blood-cells2. COVID-19 chest X-ray dataset: https://www.kaggle.com/pranavraikokte/covid19-image-dataset3. Brain MRI images for brain tumour detection: https://www.kaggle.com/navoneel/brain-mriimages-for-brain-tumor-detectionAPPENDIX AMarking criteria GradeCriteria70– 100%A mark of 70% or over is indicative of excellent work where the student hasmore than met the requirements of the assessment brief and demonstratedan exceptional understandingof deep learningmodels, tools and techniquesalong with knowledge of theirchosen dataset and provides a comprehensivecritical view of the workflowof these models andexcellent presentation ofthe results by distinctive visualisations.60– 69%A mark within this range is highly competent and completed to a highstandard. The work demonstrates a good level of understanding ofdeeplearning modelsalong with knowledge of theirchosen dataset and providesa comprehensivecritical view of the workflowof these models andgoodpresentation of the results by visualisations. The requirements of theassessment brief have been met to a high standard but with room for a fewminor areas of improvement. Marks at the lower end in this band suggestthat students have met all or most of the requirements of the assessmentbrief but there are a larger number of minor areas needing improvement.50– 59%A mark within the range indicates a pass, where the work has beencompleted to a satisfactory standard, but where there is still significantscope for improvement. The work demonstrates an acceptableunderstanding ofdeep learning tools and techniques along with a reasonableknowledge of theirchosen dataset and provides a reasonably welldocumented account of the workflowof these models. The work will havecovered most of the key assessment criteria, but these might be at a moresuperficial level compared with work in the higher mark ranges, withevidence of a less complete understanding of the subject area. The work mayindicate that less independent learning has been performed or that lessrobust methods are used.40– 59%Thisindicates afail mark, where learning outcomes may not all have beenmet to a satisfactory standard and where there may be a range of omissions,poor communication and/or possibly a lack of knowledge derived fromwider reading. The work does not demonstrate an acceptableunderstandingofdeep learning models, nor provides a well-documented account ofworkflowof these models. Work in this mark range indicates insufficientevidence of an understanding of the subject area appropriate to level 7,and/or that insufficient attention has been given to the assessment brief.15– 39Thisindicate afail mark, indicating a piece of work which is below theacceptable standard and which provides little evidence of the skills, %understanding or knowledge appropriate to level 7. There may be manyerrors and omissions, and few or no of the learning outcomes have been met,with an inadequate demonstration of the knowledge required of keydeeplearning models/tools and techniques and their applications. Instructionsmay not have been followed or assessment criteria may have been missedout.0– 14%missingmostly irrelevant.
- Assignment status: Already Solved By Our Experts
- (USA, AUS, UK & CA PhD. Writers)
- CLICK HERE TO GET A PROFESSIONAL WRITER TO WORK ON THIS PAPER AND OTHER SIMILAR PAPERS, GET A NON PLAGIARIZED PAPER FROM OUR EXPERTS