CSI643 Assignment, Page 1 of 2 Semester 1 2021/2022
CSI643: Machine Learning
Answer all questions. 100 marks maximum.
Assigned: Wednesday 3rd November 2021
Part 1 Due: Tuesday 9th November 2021
Part 2 Due: Wednesday 24th November 2021
This assignment must be done be each student individually, without help from others. Any
use of tutorials or other documentation must appear in the bibliography and cited.
15 marks 1. Prepare a PowerPoint/pdf presentation on Python and TensorFlow and their use in
Machine Learning (maximum 20 slides). This presentation will be made during the
Wednesday 10th November lecture on Teams. The slides should be submitted using the
Assignment Part 1 (SUBMIT HERE) link on Moodle by 12 noon Tuesday 9th November
2021.
85 marks 2. You are to select one dataset from the the following URL: https://archive.ics.uci.
edu/ml/datasets.php?format=&task=reg&att=&area=&numAtt=less10&numIns=100to1000&
type=mvar&sort=nameUp&view=table. Let me know by the 4th of November 10am via
email, your first, second, and third choice. First come, first served. Implement the
following algorithms to work with the selected data set.
(i) Linear Regression.
(ii) Random Forest.
(iii) K-Nearest Neighbor.
(iv) Multi-layer Perceptron (feed forward).
Your implementation must be done using Python 3 in the Google Colab environment
(https://colab.research.google.com/), in a Jupyter Notebook. You must make
use of text cells, as well as code cells, for detailed comments explaining your code.
Your implementation must generate output as it executes, and there must be final output summarizing the results. Your notebook should be named StudentIDa2.ipynb e.g.
202312345a2.ipynb. You must use a user interface control which prompts the user to
upload your data file. Your data file in original format must also be submitted. Make
a comparison of the algorithms using the selected data set. Comparison should be submitted as a pdf file with file name StudentIDa2.pdf e.g. 202312345a2.pdf. Comparison
of the algorithms in Step 2 should be made according to the following criteria.
(a) Performance results using two (2) suitable metrics; the same for all algorithms.
(b) Description of the models used.
(c) Tuning of hyper-parameters.
(d) Pre-processing required.
(e) Explanation of effort required to implement the algorithms.
(f) Estimation of execution time for training and testing.
Please go on to the next page. . .
CSI643 Assignment, Page 2 of 2 Semester 1 2021/2022
(g) Suitability of algorithm for the data set.
(h) How your results compare with those in the literature for the same data set.
(i) Suitability of algorithm for the problem and data set.
(j) Two additional criteria not listed above.
(k) All sources used must be listed in a bibliography at the end of the pdf.
(l) Make the formatting presentable.
Zip your .ipynb, .pdf, and data file in an archive named a2.zip and submit using the
Assignment Part 2 (SUBMIT HERE) link on Moodle.
End of Assignment
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of