Faculty of Engineering and Information Technology School of Software
42028: Deep Learning and Convolutional Neural Networks Autumn 2019
ASSIGNMENT-1 SPECIFICATION
Due date Friday 11:59pm, 19 April 2019 (Extended!)
Demonstrations Marks
Submission
Optional, If required.
30% of the total marks for this subject
1. AreportinPDForMSWorddocument(5-pagesmax) 2. GoogleColab/iPythonnotebooks
Submit to
Note: This assignment is individual work.
UTS Online assignment submission
Summary
This assessment requires you to develop three different classifiers namely, KNN, SVM and Neural network, for handwritten digit classification. The features to used for classification can be either Histogram-Of-Oriented-Gradients (HoG) or Local Binary Pattern(LBP), and raw images/pixels.
Students need to provide the code (ipython Notebook) and a final report for the assignment, which will outline a brief comparative study of the classifier’s performance.
Assignment Objectives
The purpose of this assignment is to demonstrate competence in the following skills.
Toensurefirmunderstandingofbasicmachinelearningbasics.Thiswillfacilitate understanding of advanced topics.
Toensurethatstudentsunderstandthebasicsofimageclassification,feature extraction using the traditional machine learning techniques.
42028: Assignment 1 – Autumn 2019 Page 1 of 4
Tasks:
Description:
1. Implement a simple kNN classifier for digit classification
2. Implement a Linear classifier using SVM for digit classification
3. Implement a Linear classifier using Neural Network for digit classification 4. Compare the three implementations in terms of classification accuracy.
Write a short report on the implementation, linking the concepts and methods learned in class, and also provide comparative study on the accuracies obtained from combination of different classifiers and features.
Features to used: Any least two from the list given below: a. HoG
b. LBP
c. Raw image/pixels values
d. Any other feature of your choice
Dataset 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 explain
the features and classifier combination used for experiments.
2. Dataset: Provide a brief description of the dataset used with some sample
images 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 other parameters used in SVM classifier; ANN: number of input neurons/nodes, activation function, loss function, output layer information etc.)
b. Experimental Results:
i. Confusion matrix for the highest accuracy achieved, with a
very short description, with some result image sample
(optional)
ii. Comparative study: sample table format
iii. Discussion: Provide your understanding on why there was an error in the accuracy, and difference in the performance of the classifiers. You may also include some image samples which were wrongly classified.
Classifier/Feature
HOG
LBP
Raw Input
KNN
SVM
ANN
42028: Assignment 1 – Autumn 2019 Page 2 of 4
4. Conclusion: Provide a short paragraph detailing your understanding on the experiments and results.
Deliverables:
5. Project Report (5 pages max)
6. Google Colab or Ipython notebook, with the code
Additional Information: Assessment Submission
Submission of your assignment is in two parts. You must upload a zip file of the Ipython/Colab notebooks and Report to UTS Online. This must be done by the Due Date. You may submit as many times as you like until the due date. The final submission you make is the one that will be marked. If you have not uploaded your zip file within 7 days of the Due Date, or it cannot be run in the lab, then your assignment will receive a zero mark. Additionally, the result achieved and shown in the ipython/colab notebooks should match the report. Penalties apply if there are inconsistencies in the experimental results and the report.
PLEASE NOTE 1: It is your responsibility to make sure you have thoroughly tested your program to make sure it is working correctly.
PLEASE NOTE 2: Your final submission to UTS Online is the one that is marked. It does not matter if earlier submissions were working; they will be ignored. Download your submission from UTS Online and test it thoroughly in your assigned laboratory.
Return of Assessed Assignment
It is expected that marks will be made available 2 weeks after the submission via UTS Online. You will be given a copy of the marking sheet showing a breakdown of the marks.
Queries
If you have a problem such as illness which will affect your assignment submission contact the subject coordinator as soon as possible.
Dr. Nabin Sharma
Room: CB11.07.124
Phone: 9514 1835
Email: Nabin.Sharma@uts.edu.au
If you have a question about the assignment, please post it to the UTS Online forum for this subject so that everyone can see the response.
If serious problems are discovered the class will be informed via an announcement on UTS Online. 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 3 of 4
following
subject outline
assignment specification
UTS Online FAQ
UTS Online discussion board
You will be directed to these locations rather than given a direct answer.
Extensions and Special Consideration
In alignment with Faculty policies, assignments that are submitted after the Due Date will lose 10% of the received grade for each day, or part thereof, that the assignment 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 an assessment task on time, please contact your subject coordinator before the assessment task is due to discuss an extension. Extensions may be granted up to a maximum of 5 days (120 hours). In all cases you should have extensions confirmed in writing.
If you believe your performance in an assessment item or exam has been adversely affected by circumstances beyond your control, such as a serious illness, loss or bereavement, hardship, trauma, or exceptional employment demands, you may be eligible to apply for Special Consideration (https://www.uts.edu.au/current- students/managing-your-course/classes-and-assessment/special- circumstances/special) .
Academic Standards and Late Penalties
Please refer to subject outline.
42028: Assignment 1 – Autumn 2019 Page 4 of 4