csu logo green Computer Science Department

Big Data: TP Proposal

CS535
Spring 2020
Home Syllabus Schedule Assignments Grading Policy Course Policy Code of Conduct Canvas

Proposal (Due on 3/31/2020 by 5:00PM)

Introduction

The purpose of the term project is for you to learn how to formulate a simple Big Data problem/task/application and to gain experience in solving it using algorithms, system design and techniques taught in class. ___________________________________________________________________________________________________

Components of the proposal report

1. Title of your project

This should be concise and self-descriptive.

2. Problem formulation

The proposal should clearly identify the problem. It should include at least one or two carefully crafted paragraph that states and highlights the problem. The problem formulation should be able to answer following questions:

  • What is the problem you are solving?   This should also include the background for the problem.
  • Why is it interesting as a Big Data problem and who would use it if it were solved?

3. Your strategy to solve the problem 

Describe your proposed approach to solve the problem. The description of the strategy should include, 

  • The algorithms/techniques/models you plan to use in this project.
    • Your data pre-processing and explorative analytics
    • Your Deep Learning model application
    • Othter models and methodologies, if applicable
  • The framework you plan to use in this project.
  • The dataset you plan to use in this project

Please note that you are also required to submit your code as a part of the final output of this project.

NOTE: Your computation requirement for this semester is "a Distributed Deep Learning". As a part of your term project, you and your team are required toperform a deep learning over a distributed computing framework. Regarding the framework, you may use PyTorch, Horovod, TensorFlow with Spark. However, we will provide a tutorial video clip for using the distributed PyTorch. We have noticed that PyTorch works well in our cluster.

Please note that your problem may not be solved with applying a deep leearning model only. Please feel free to combine with other algorrithms if neeeded.

4. Evaluation method 

The proposal should include an evaluation plan including metrics that you will use to identify if you have succeeded or not.  If you come up with a metric, also provide an intuitive feel for what this metric captures and why you think this is appropriate.

For example, if your project involves classification, you can list accuracy measures that will be used and provide justification.

5. Project timeline (weekly plan)

You should provide a table with a weekly plan to complete the term project. If you have teammate, the plan should also include information about the respective roles.

6. Bibliography

Included a bibliography.  All references must be cited in the report. 

  • The authors' names
  • The titles of the works
  • The names of publisher
  • The date (or year) the copies were published
  • The page numbers of your sources (if available)

7. Submission

If it is a team submission, please submit only one copy of and specify the team members in the author list associated with the document.

This document should be up to 1,500 ~ 2,000 words. Do not exceed the limit.

There will be no presentation for the term proposal this semester.

 



 

 


Home Syllabus Schedule Assignments Grading Policy Course Policy Code of Conduct Canvas