Machine Learning Practical (MLP) 2018-19: Group Project

Overview

MLP in semester 2 will be based on projects done in groups of 2-3 students. The projects, which should be done using one of the deep learning toolkits (TensorFlow or PyTorch is recommended), can be chosen from a variety of topics and data sets.

Project Groups

The projects are intended to be done in groups of 2-3 students. By working in a small group you can discuss ideas and work things out together. You can form your own groups. You can use the Piazza 'Search for Teammates' to help you form a group, if you like.

You may discuss any aspects of the assignment with your group and divide up the tasks however you wish; but we encourage you to collaborate on each part rather than doing a strict division of tasks, as this will enable better learning for all of you.

For more details about the project process, please see the slides for lecture 11 in semester 1. We also prepared a project discovery guide, which also includes ideas for possible projects

Interim Report

The interim report for your project should include the the motivation and introduction to your project, the objectives, the data set and task, the methodology, the first phase of experiments, and a plan for the rest of the project.

The interim report for your project should be submitted as Coursework 3, by 16:00 on Thursday 14 February 2019. The interim report marking will only consist of feedback only, there will be no numerical mark.

Coursework 3 (interim report) description
Latex template for interim report: mlp-cw3-template.zip

Final Report

The final report for your project will have a focus on the main experiments, results, interpretation, related work, and conclusions.

The final report for your project should be submitted as Coursework 4, by 16:00 on Friday 22 March 2019. The final report mark is worth 50% of the mark for the course.

Coursework 4 (final report) description

IBM Prize

For a second year, IBM UK have kindly donated a prize for the best project in MLP. Reports and presentations for the prizewinning and shortlisted projects in MLP in 2017/18.

Project discovery guide, and ideas for possible projects

Copyright (c) University of Edinburgh 2015-2018
The MLP course material is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
licence.txt
The software at https://github.com/CSTR-Edinburgh/mlpractical is licensed under the Modified BSD License.
This page maintained by Steve Renals.
Last updated: 2019/09/16 15:42:09UTC

Home : Teaching : Courses : Mlp