Taking causal inference to the extreme!
-
Updated
Jun 2, 2024 - Julia
Taking causal inference to the extreme!
This code is for the honour thesis developed by Dannong Xu. It includes CTNet (developed algorithm in the thesis), Siamese Network, MAML, and Reptile.
Generalizing to New Physical Systems via Context-Informed Dynamics Model
Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"
A project implementing better evaluation scenarios for community models for malicious content detection, and meta-learning GNNs to achieve better downstream adaptation.
Code for the paper "Benchmarking AutoML solutions for Clusering"
autoEnsemble : An AutoML Algorithm for Building Homogeneous and Heterogeneous Stacked Ensemble Models by Searching for Diverse Base-Learners
Skin lesion image analysis that draws on meta-learning to improve performance in the low data and imbalanced data regimes.
Image classification with very few data sample (n=25 per class)
Code for the research paper Meta-learning with hierarchical models based on similarity of causal mechanisms
Uncertainty-Guided Online Test-time Adaptation via Meta-Learning
SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence
Implementation of Jump-Start Reinforcement Learning (JSRL) with Stable Baselines3
Python Meta-Feature Extractor package.
Automated Machine Learning with scikit-learn
The objective of this report is to conduct a study on the images of dogs and classify the emotions of each dog using deep learning algorithms, and to provide an new approach to solve this particular classification problem
This repository is the code base for the project titled Latent Embedding Optimization for Few-shot Segmentation.
MetaTS | Time Series Forecasting using Meta Learning
Latent graphs (reward landscapes). Can humans learn them? How?
Add a description, image, and links to the metalearning topic page so that developers can more easily learn about it.
To associate your repository with the metalearning topic, visit your repo's landing page and select "manage topics."