This repository contains the code development aiming to address the identifiability issue in noisy label learning through the lens of multinomial mixture models.

Personal website made from Quarto

Mixup on the Chaoyang dataset

Implementation of DC-GAN and its variant - class conditional DC-GAN in Jax

Implementation of "Learning to defer" in JAX

Implementation of SimCLR v1 in Jax

This is the official implementation for the paper "Task weighting in meta-learning with trajectory optimisation"

Implementations of many meta-learning algorithms to solve the few-shot learning problem in Pytorch

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

Implementation of "Probabilistic task modelling for meta-learning" accepted at UAI 2021.

This is an un-official github page for the course Foundation of Computer Science at the University of Adelaide.

Official implementation of the paper "Similarity of classification tasks" accepted at Neurips meta-learning workshop 2020