$\newcommand{\xv}{\mathbf{x}} \newcommand{\Xv}{\mathbf{X}} \newcommand{\yv}{\mathbf{y}} \newcommand{\zv}{\mathbf{z}} \newcommand{\av}{\mathbf{a}} \newcommand{\Wv}{\mathbf{W}} \newcommand{\wv}{\mathbf{w}} \newcommand{\tv}{\mathbf{t}} \newcommand{\Tv}{\mathbf{T}} \newcommand{\muv}{\boldsymbol{\mu}} \newcommand{\sigmav}{\boldsymbol{\sigma}} \newcommand{\phiv}{\boldsymbol{\phi}} \newcommand{\Phiv}{\boldsymbol{\Phi}} \newcommand{\Sigmav}{\boldsymbol{\Sigma}} \newcommand{\Lambdav}{\boldsymbol{\Lambda}} \newcommand{\half}{\frac{1}{2}} \newcommand{\argmax}[1]{\underset{#1}{\operatorname{argmax}}} \newcommand{\argmin}[1]{\underset{#1}{\operatorname{argmin}}}$

Project Proposal for CS445, Spring, 2019

Type your name here

Introduction

Your project may involve one or more than one of the following steps.

  • Apply a neural network learning algorithm and implementation covered in class applied to a data set of interest to you. Analyze the results, in terms of training and testing accuracy, data samples for which the neural network output is incorrect, and displays of activities and/or weights in hidden units to help understand how the neural network is making its decisions.
  • Download code from the net that implements an algorithm covered in class or a new one, and apply it to data of interest to you. Analyze the results, in terms of training and testing accuracy, data samples for which the neural network output is incorrect, and displays of activities and/or weights in hidden units to help understand how the neural network is making its decisions.
  • Study at least five research articles from which you can learn about a machine learning topic of interest to you. Your project will be a written report summarizing each article and describing similarities and differences between the papers, along with a detailed discussion of what you learned.

Methods

Explain why you wish to do the proposed project and the steps you will need to take to complete the project. Describe the methods you will use. What are the sources of code or data? Will you define new algorithms and/or implementations, or use ones from class, or download ones from an on-line source?

If you will be working with others, define exactly what each team member will be working on.

Possible Results

Speculate on possible answers to the questions you provide in the Introduction.

Timeline

Make a list with at least four entries with dates and describe what each team member will accomplish by these dates. This is for your use. Your grade will not depend on meeting these deadlines.

Check-in

Do not include this section in your notebook.

Name your notebook Lastname-proposal.ipynb. So, for me it would be Anderson-Proposal.ipynb. Submit the file using the Project Proposal link on Canvas.

Grading will be based on

  • clarity of describing your motivation and methods,
  • division of work among team members, if applicable.

The instructor may ask you to expand your project and resubmit your proposal.