mdsthesis

A repository for the code for my MEng (Data Science) thesis project.

https://github.com/alexredplanet/mdsthesis

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

A repository for the code for my MEng (Data Science) thesis project.

Basic Info
  • Host: GitHub
  • Owner: alexredplanet
  • Language: Python
  • Default Branch: main
  • Size: 1.41 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme Citation

README.md

MDSThesis

Author: Alexander Mars Supervised by Vinoth Nandakumar and Tonglian Liu (All from University Of Sydney).

This code is part of the submission for the Master Of Data Science Capstone project. The thesis is titled "Want to get robust? Time to lose weights.", this project focuses on using sparsity for learning with noisy labels.

To run the code, extract an experiment file from the experiments folder into the parent directory (this directory) and then simply run python3 ExperimentX.py. Scripts for submission to a pbs-based linux computing cluster are also included. Refer to these scripts for the estimated run-time.

Parts of the code have been modified from these sources: - Shiwei Liu, Lu Yin, Decebal Constantin Mocanu and Mykola Pechenizkiy, "Do we actually need dense over-parameterization? in-time over-parameterization in sparse training", International Conference on Machine Learning, 2021. - Multi-class peer loss functions - https://github.com/weijiaheng/Multi-class-Peer-Loss-functions/tree/main/CIFAR-10 - Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin, "Layerwise Sparsity for Magnitude-based Pruning", ICLR 2021.

Please reference this repository if you use it!

Owner

  • Login: alexredplanet
  • Kind: user

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Want to get robust? Time to lose weights.
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - name-particle: Alexander
    family-names: Mars
    affiliation: The University Of Sydney
    orcid: 'https://orcid.org/0000-0001-5947-5252'
  - name-particle: Vinoth
    family-names: Nandakumar
    affiliation: The University Of Sydney
  - name-particle: Tongliang
    family-names: Liu
    affiliation: The University Of Sydney

GitHub Events

Total
Last Year