This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"

Reproducing RigL (ICML 2020) as a part of ML Reproducibility Challenge 2020

Editorial venue for ML Reproducibility Challenge Accepted papers

Code for our Reproducibility Challenge Paper "On end-to-end 6DoF object pose estimation and robustness to object scale"

Replication of the novel Generative Adversarial Transformer.

Detection and attribution of climate change using deep learning

Learning the Underlying Physics of a Simulation Model of the Ocean's Temperature

Testing the Reproducibility of the paper: MixSeq. Under the assumption that macroscopic time series follow a mixture distribution, they hypothesise that lower variance of constituting latent mixture components could improve the estimation of macroscopic time series.

A preliminary analysis into the effort required for reproducing computational science scholarly articles.

Variational data assimilation with deep prior

Code, data and results of a reproducibility experiment for the paper "Exploring the Representation of Word Meanings in Context" by Marcos Garcia.

Assignments for COMP 551: Applied Machine Learning at McGill University

Reproducibility Challenge 2020 papers

A bioinformatics pipeline for RNA-Seq analysis of Staphylococcus aureus persisters under antibiotic stress, based on Peyrusson et al. (2020). Built with Nextflow and Docker for reproducibility.

A reproducibility study for the paper MAGE: Machine-generated Text Detection in the Wild, implementing Longformer and DistilBERT models to detect machine-generated text across diverse domains. This repository includes datasets, scripts, and evaluation metrics for benchmarking detection performance.