42028: Assignment 1 – Autumn 2019 Page 1 of 4Faculty of Engineering and Information TechnologySchool of Software42028: Deep Learning and Convolutional Neural NetworksAutumn 2019ASSIGNMENT-1 SPECIFICATIONDue date Friday 11:59pm, 19 April 2019 (Extended!)Demonstrations Optional, If required.Marks 30% of the total marks for this subjectSubmission 1. A report in PDF or MS Word document (5-pages max)2. Google Colab/iPython notebooksSubmit to UTS Online assignment submission Note: This assignment is individual work.SummaryThis assessment requires you to develop three different classifiers namely, KNN,SVM and Neural network, for handwritten digit classification. The features to usedfor classification can be either Histogram-Of-Oriented-Gradients (HoG) or LocalBinary Pattern(LBP), and raw images/pixels.Students need to provide the code (ipython Notebook) and a final report for theassignment, which will outline a brief comparative study of the classifier’sperformance.Assignment ObjectivesThe purpose of this assignment is to demonstrate competence in the followingskills. To ensure firm understanding of basic machine learning basics. This will facilitateunderstanding of advanced topics. To ensure that students understand the basics of image classification, featureextraction using the traditional machine learning techniques.42028: Assignment 1 – Autumn 2019 Page 2 of 4Tasks:Description:1. Implement a simple kNN classifier for digit classification2. Implement a Linear classifier using SVM for digit classification3. Implement a Linear classifier using Neural Network for digit classification4. Compare the three implementations in terms of classification accuracy.Write a short report on the implementation, linking the concepts and methodslearned in class, and also provide comparative study on the accuracies obtainedfrom combination of different classifiers and features.Features to used: Any least two from the list given below:a. HoGb. LBPc. Raw image/pixels valuesd. Any other feature of your choiceDataset to be used: MNIST (English handwritten numerals).Report Structure:The report should include the following sections:1. Introduction: Provide a brief outline of the report and also briefly explainthe features and classifier combination used for experiments.2. Dataset: Provide a brief description of the dataset used with some sampleimages of each class.3. Experimental results and discussion:a. Experimental settings: Provide information on the classifier settings(e.g: KNN: value of k for kNN classifier; SVM: kernel and otherparameters used in SVM classifier; ANN: number of inputneurons/nodes, activation function, loss function, output layerinformation etc.)b. Experimental Results:i. Confusion matrix for the highest accuracy achieved, with avery short description, with some result image sample(optional)ii. Comparative study: sample table formatClassifier/Feature HOG LBP Raw Inputiii. Discussion: Provide your understanding on why there was anerror in the accuracy, and difference in the performance of theclassifiers. You may also include some image samples whichwere wrongly classified.42028: Assignment 1 – Autumn 2019 Page 3 of 44. Conclusion: Provide a short paragraph detail代写42028留学生作业、代做Neural Networks作业、Python程序作业代写、代做Python语言作业 代ing your understanding on theexperiments and results.Deliverables:5. Project Report (5 pages max)6. Google Colab or Ipython notebook, with the codeAdditional Information:Assessment SubmissionSubmission of your assignment is in two parts. You must upload a zip file of theIpython/Colab notebooks and Report to UTS Online. This must be done by the DueDate. You may submit as many times as you like until the due date. The finalsubmission you make is the one that will be marked. If you have not uploaded your zipfile within 7 days of the Due Date, or it cannot be run in the lab, then your assignmentwill receive a zeromark. Additionally, the result achieved and shown in theipython/colab notebooks should match the report. Penalties apply if there areinconsistencies in the experimental results and the report.PLEASE NOTE 1: It is your responsibility to make sure you have thoroughly tested yourprogram to make sure it is working correctly.PLEASE NOTE 2: Your final submission to UTS Online is the one that is marked. It doesnot matter if earlier submissions were working; they will be ignored. Download yoursubmission from UTS Online and test it thoroughly in your assigned laboratory.Return of Assessed AssignmentIt is expected that marks will be made available 2 weeks after the submission via UTSOnline. You will be given a copy of the marking sheet showing a breakdown of the marks.QueriesIf you have a problem such as illness which will affect your assignment submissioncontact the subject coordinator as soon as possible.Dr. Nabin SharmaRoom: CB11.07.124Phone: 9514 1835�If you have a question about the assignment, please post it to the UTS Online forumfor this subject so that everyone can see the response.If serious problems are discovered the class will be informed via an announcement on UTSOnline. It is your responsibility to make sure you frequently check UTS Online.PLEASE NOTE : If the answer to your questions can be found directly in any of the 42028: Assignment 1 – Autumn 2019 Page 4 of 4following subject outline assignmentspecification UTS Online FAQ UTS Online discussion boardYou will be directed to these locations rather than given a direct answer.Extensions and Special ConsiderationIn alignment with Faculty policies, assignments that are submitted after the DueDate will lose 10% of the received grade for each day, or part thereof, that theassignment is late. Assignments will not be accepted after 5 days after the Due Date.When, due to extenuating circumstances, you are unable to submit or present anassessment task on time, please contact your subject coordinator before theassessment task is due to discuss an extension. Extensions may be granted up to amaximum of 5 days (120 hours). In all cases you should have extensions confirmed inwriting.If you believe your performance in an assessment item or exam has been adverselyaffected by circumstances beyond your control, such as a serious illness, loss orbereavement, hardship, trauma, or exceptional employment demands, you may beeligible to apply for Special Consideration (https://www.uts.edu.au/currentstudents/managing-your-course/classes-and-assessment/specialcircumstances/special).Academic Standards and Late PenaltiesPlease refer to subject outline.转自：http://www.7daixie.com/2019042217731884.html
网友评论