- 1 -
Applied Machine Learning Systems ELEC0134 (20/21)
Assignment
General Overview
The AMLS assignment comprises individual code writing, training and testing on data, and
an individual report in the form of a conference paper and (optionally) supplementary mate-
rial. You are allowed to discuss ideas with peers, but your code, experiments and report
must be done solely based on your own work.
Assignment summary
1. The assignment leverages elements covered in:
a. The AMLS lectures,
b. The AMLS lab sessions, and
c. Relevant research literature associated with machine learning systems.
The assignment involves the realisation of various machine learning tasks on a pro-
vided dataset. You are expected to go through the data, analyse it and/or pre-pro-
cess it as necessary.
2. Using your ML knowledge acquired in the lectures and the labs, design solutions for
each task described in the section Assignment Description below. You should also
search the relevant literature for additional information, e.g., papers on state-of-the-
art methods in machine learning.
3. Implement your solution in your preferred programming language, e.g., MATLAB, Py-
thon, C/C++, Java, etc. However, please note that the weekly exercise of the module
will be based on Python, so you are encouraged to use this programming language
too.
4. Write a report summarising all steps taken to solve the tasks, explaining your model
and design choices. In addition, in the report, you should also describe and analyse
the results obtained via your experiments and provide accuracy prediction scores on
unseen data. Please refer to Report and Code Format and Marking Criteria section
for more details about the report.
Goal of the assignment
• To further develop your programming skills.
• To further develop your skills and understanding of machine learning systems.
• To acquire experience in dealing with real-world data.
• To develop good practice in model training, validation and testing.
• To read state-of-the-art research papers on machine learning systems and under-
stand the current challenges and limitations.
• To develop your writing skills by presenting your solutions and findings in the form
of a conference paper.
- 2 -
Assignment Description
Datasets
We provide two datasets which are designed specifically for this assignment and contains
pre-processed subsets from the following datasets:
1. CelebFaces Attributes Dataset (CelebA), a celebrity image dataset (S. Yang, P. Luo, C.
C. Loy, and X. Tang, "From facial parts responses to face detection: A Deep Learning
Approach", in IEEE International Conference on Computer Vision (ICCV), 2015)
2. Cartoon Set, an image dataset of random cartoons/avatars (source:
https://google.github.io/cartoonset/).
The datasets you are going to use in this assignment are:
1. celeba: A sub-set of CelebA dataset. This dataset contains 5000 images. It is going to
be used for task A1 and A2.
2. cartoon_set: A subset of Cartoon Set. This dataset contains 10000 images. It is going
to be used for task B1 and B2.
The datasets can be downloaded via following link:
https://drive.google.com/file/d/1wGrq9r1fECIIEnNgI8RS-_kPCf8DVv0B/view?usp=sharing
A separate test set will be provided one week before the deadline.
Tasks
The machine learning tasks include:
A. Binary tasks (celeba dataset)
A1: Gender detection: male or female.
A2: Emotion detection: smiling or not smiling.
B. Multiclass tasks (cartoon_set dataset)
B1: Face shape recognition: 5 types of face shapes.
B2: Eye color recognition: 5 types of eye colors.
You should design separate modes for each task and report training errors, validation er-
rors, hyper-parameter tuning. You are allowed to use the same model/methodology for dif-
ferent tasks, but you must explain the reason behind choices. If you tried several models for
one task, feel free to show them in your code and compare the results in the report.
Report and Code Format, and Marking Criteria
Report format and template
We provide both latex and MS word templates in AMLS_assignment_kit. The criteria for
each part are detailed in the template. For beginners in latex, we recommend overleaf.com,
which is a free online latex editor.
Your report should be no longer than 8 pages (including the reference). You are allowed to
append an additional supplementation material to your report with no longer than 4 pages.
- 3 -
Once you finish your report, please export it into a PDF document and name it with the fol-
lowing format (Using your SN number):
Report_AMLS_20-21 _SN12345678.pdf
Code criteria
You should write your code in modules and organize them in the following fashion:

• Keep ‘Dataset’ folder empty while submitting your code. Use this folder for your pro-
gramming only. If you need to pre-process the dataset, do not save the intermediate
results or pre-processed dataset. Your final submission must directly read the files
we provided.
• When assessing your code, we will copy-paste the dataset into this folder. Then,
your project should look like:
o AMLS_20-21_SN12345678
§ A1
§ A2
§ B1
§ B2
§ Datasets
• cartoon_set
• celeba
• cartoon_set_test
• celeba_test
§ main.py
§ README.md
• The ‘A1’, ‘A2’, ‘B1’ and ‘B2’ folders should contain the code files for each task.
• Pre-trained models (especially for deep learning models) are allowed to be saved in
the folder for each task.
• The README file should contain:
o a brief description of the organization of your project;
o the role of each file;
o the packages required to run your code (e.g. numpy, scipy, etc.).
The recommend format for README file is markdown (.md). .txt is acceptable
too.
• We should be able to run your project via ‘main.py’. An example structure of
‘main.py’ has been provided for your reference.
- 4 -
• You are NOT going to upload your code and dataset to Moodle. Please refer to Sub-
mission session for more details.
Marking scheme
The mark will be decided based on both the report and corresponding code. In particular,
we will mark based on following scheme:
REPORT 60% CORRESPONDING CODE 40%
Abstract 5%
Introduction 7%
Literature survey 15%
Description of models (Use
flow charts, figures, equations
etc. to explain your models
and justify your choices)
Task A1 2%
Task A2 2%
Task B1 2%
Task B2 2%
Implementation (the details of
your implementation, explain
key modules in your code.)
Task A1 3% Correct implementation 7%
Task A2 3% Correct implementation 7%
Task B1 3% Correct implementation 7%
Task B2 3% Correct implementation 7%
Experimental Results and Anal-
ysis
Task A1 2% Reasonable results 3%
Task A2 2% Reasonable results 3%
Task B1 2% Reasonable results 3%
Task B2 2% Reasonable results 3%
Conclusion 5%

It should be noted that – whereas we expect students to develop machine learning models
delivering reasonable performance on tasks A1, A2, B1 and B2 – the assessment will not be
based on the exact performance of the models. Instead, the assessment will predominantly
concentrate on how you articulate about the choice of models, how you develop/train/vali-
date these models, and how you report/discuss/analyse the results.
Submission
• Deadline: See Moodle.
• Report submission: you should only submit your report on Moodle:
• Code submission: You must include a link to your code in a repository that is publicly
accessible in your report, but the link is hidden (e.g., GitHub, public Dropbox or
Google Drive link, or similar).
You are encouraged to use GitHub to save and track your project as we expect to see
you progress your assignment gradually. Use your UCL GitHub account (or create an
account) to start a git repository named
AMLS_assignment20_21/
Make sure to back-up your code on the git repository regularly and keep your reposi-
tory private so it is not viewable by other students. Changes made after the assign-
ment deadline will not be taken into account. The code should be well documented
- 5 -
(i.e., each class and function should be commented) and an additional README.md
file containing instructions on how to compile and use your code should be created
in the repository. We reserve the right to test the code and we may ask you to pro-
vide us with your GitHub commit history evidencing how you gradually built and
tested your solution.

欢迎咨询51作业君