This is a repository for CS4ML. It is a general framework for active learning in regression problems. It approximates a target function arising from general types of data, rather than pointwise samples.

Active Learning combining Online Semi-Supervised Dictionary Learning

Active learning-guided exploration of parameter space of air plasmas to enhance the energy efficiency of NO x production

The KSLCL-DCEE algorithm for auto-optimization

Project source code and data for risk estimation with an imperfect Machine learning model

This is a repository associated with the paper "Near-optimal sampling strategies for multivariate function on general domains" by Ben Adcock and Juan M. Cardenas available at https://epubs.siam.org/doi/10.1137/19M1279459 and https://arxiv.org/abs/1908.01249

Bayesian Active Learning for Remote Sensing

Active versus Passive exploration

Quantile set inversion [arXiv:2211.01008] — Numerical experiments

Gaussian Processes for Cyclic Voltammetry

The code of ''Single Shot Active Learning using Pseudo Annotators"

A toolbox for Weighted Sparse Simplex Representation (WSSR).

Language Agnostic Syllabification with Active Learning

Domain Adaptation by Transferring Model-Complexity Priors Across Tasks Paper Experiments

ALPUD: Active Learning from Positive and Unlabeled Data

Matlab code of the IRD algorithm in the paper: 刘子昂, 蒋雪, 伍冬睿, "基于池的无监督线性回归主动学习," 自动化学报, 2020. Or the English version here: https://arxiv.org/pdf/2001.05028.pdf

This repository contains the code to reproduce all of the results in our paper: Nuclear discrepancy for single-shot batch active learning, Tom J Viering, Jesse H Krijthe, Marco Loog, in Machine Learning 2019.

Matlab source code of the paper: D. Wu, "Pool-based sequential active learning for regression," IEEE Trans. on Neural Networks and Learning Systems, 30(5), pp. 1348-1359, 2019.

Active Learning Project