CS 254 Machine Learning
Project Proposal Report Format
Below are guidelines on how to write-up your proposal report for the course project:
1. Introduction
Motivate and abstractly describe the problem you are addressing and how you are
addressing it. What is the problem? Why is it important? What is your basic
approach? A short discussion of how it fits into related work in the area is also
desirable. Summarize the basic results and conclusions that you will achieve.
2. Problem Definition and Algorithm
2.1 Task Definition
Precisely define the problem you are addressing (i.e. formally specify the inputs and
outputs). Elaborate on why this is an interesting and important problem.
2.3. Dataset
Answer all the questions related to your dataset, such as: Describe your dataset? is
your dataset available? is it labeled, or do you need an effort to label it (how? when ?
how many samples do you need to label?)? Do you need special hardware to process
your data? Etc …
2.2 Algorithm Definition
Describe in reasonable detail the algorithm you are using to address this problem.
Explain your baseline system and justify the choice of the baseline system? Do you
have the plan to use other techniques or do you want to extend or enhance the current
baseline system? Elaborate here and discuss different scenarios that you might
approach. A psuedocode description of the algorithm you are using is frequently
useful.
3. Experimental Evaluation
3.1 Methodology
What are the criteria you are using to evaluate your method? What specific
hypotheses do your experiment test? Describe the experimental methodology that you
used, and why do you think it is the right way to measure the performance. What is
the training/test data that was used, and why is it realistic or interesting? Exactly what
performance data did you collect and how are you presenting and analyzing it?
Comparisons to competing methods that address the same problem are useful.
3.2 Results
Present the quantitative results of your baseline system experiments. Graphical data
presentation such as graphs and histograms are frequently better than tables.
3.3 Discussion
Is your hypothesis supported? What conclusions do the results support the strengths
and weaknesses of your method compared to other methods? How can the results be
explained in terms of the underlying properties of the algorithm and/or the data? What
is your target/goals to achieve by the end of the semester?
4. Related Work
Answer the following questions for each piece of related work that addresses the same
or a similar problem. What are their problems and methods? How is your problem
approach could be different or better?
5. Next Steps
- Precisely describe your next steps toward the final project objectives and how
you will approach them. Elaborate enough to recognize your next steps
including methods, timeline, etc…
- Explicitly define the role of each student on the project, make sure that
each student will develop or participate in developing a machine learning
algorithm.
5. Code and Dataset
Share the code and the dataset (don’t share private datasets), describe in precise and
clear steps how to reproduce the results you achieved. Sharing the code and the steps
using GitHub or gitlab would be great and enough!
6. Conclusion
Briefly summarize the important results and conclusions presented in the report.
summarize the most important points illustrated by your work? summarize how will
your results improve by enhancing the current approach or using different approaches.
Bilbiography
Be sure to include a standard, well-formatted, comprehensive bibliography with
citations from the text referring to previously published papers in the scientific
literature that you utilized or are related to your work. Include references to the public
code that you used for your project.
