Project

Note on Teams

You are allowed to work in groups of up to three people.

---

Project Proposal

Released Date: 08/29/17

Due Date: 09/28/17

The project proposal report should be in the form of a conference submission, we will follow CVPR’s submission format [link]. You are required to typeset it in $\LaTeX$.

Part 1: Assignment

There are two options for the project:

• Explore the revelvant models and techniques covered in this course on a problem of your interest. This could be releated to your research.
• Reproduce an existing work related to the materials covered in this course.

The project proposal should contain the following parts:

1. Introduction and Project Descriptions
2. Proposed Method
3. Dataset Description
4. Proposed Experiments
5. Resource Feasibility
6. Tentative timeline and the necessary steps
7. Referenes

Part 2: Submit

Hand in assignment on compass.

The project proposal should be in pdf format. File name should be net_id_project_proposal (e.g yeh17_project_proposal.pdf)

For groups of two or more, only one team member should submit the project proposal. File name should be net_ids_project_proposal.pdf (e.g. yeh17_yeh17_project_proposal.pdf)

---

Written Report

Released Date: 08/29/17

Due Date: 12/18/17

The written report should be in the form of a conference submission, we will follow CVPR’s submission format [link]. You are required to typeset it in $\LaTeX$.

Part 1: Assignment

The written report should contain the following parts (a total of 6 pages including reference page):

• Background Section: Describing the content of at least one interesting article from the pattern recognition literature (machine learning, signal processing, or some related area)
• Method Section: Overall method on how you achieved to solved the proposed problem, and a bit of original derivation that has some relevance to what you’re trying to accomplish.
• Experiment Section: Describing the experiments you ran and the results.
• Conclusion and Future Work: Discussion and future work.
• References: List of references.

Part 2: Code

• Code Description + Code: Well documented code and code submission. Note: significant similarity in code of online sources will result in loss of points.

Part 3: Submit

• Hand in report on compass.

The project proposal should be in pdf format. File name should be net_id_project_report (e.g yeh17_project_report.pdf)

For groups of two or more, only one team member should submit the project report. File name should be net_ids_project_report.pdf (e.g. yeh17_yeh17_project_report.pdf)

• Check code into one of the group memeber’s svn repository (specify the netid in the report), with the directory name final_project

---

List of Topics

• Comparing logitistic regression and linear regression.
• Comparing different optimization method emperically.
• Proof for optimization, (e.g. derive convergence properties for Stochastic gradient descent.)
• Investigate in kernel methods for svm.
• Implement a deep neural network library.
• Deep learning for application X.
• Comparison of different MRF inference techniques.

Feel free to post on Piazza for project idea discussions.