Active Learning

312 papers with code • 0 benchmarks • 13 datasets

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Latest papers without code

MOFSimplify: Machine Learning Models with Extracted Stability Data of Three Thousand Metal-Organic Frameworks

no code yet • 16 Sep 2021

We assess the validity of our NLP methods and the accuracy of our extracted data by comparing to a hand-labeled subset.

Active Learning

FOMO: Topics versus documents in legal eDiscovery

no code yet • 16 Sep 2021

This paper makes the argument that eDiscovery is the process of identifying responsive information, not identifying documents.

Active Learning

Mitigating Sampling Bias and Improving Robustness in Active Learning

no code yet • 13 Sep 2021

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness.

Active Learning

Improving Robustness and Efficiency in Active Learning with Contrastive Loss

no code yet • 13 Sep 2021

This paper introduces supervised contrastive active learning (SCAL) by leveraging the contrastive loss for active learning in a supervised setting.

Active Learning Out-of-Distribution Detection

Adaptive network reliability analysis: Methodology and applications to power grid

no code yet • 11 Sep 2021

Flow network models can capture the underlying physics and operational constraints of many networked systems including the power grid and transportation and water networks.

Active Learning

Active learning for reducing labeling effort in text classification tasks

no code yet • 10 Sep 2021

Furthermore, we explore the influence of the query-pool size on the performance of AL.

Active Learning Classification +1

Open-World Active Learning with Stacking Ensemble for Self-Driving Cars

no code yet • 10 Sep 2021

The environments, in which autonomous cars act, are high-risky, dynamic, and full of uncertainty, demanding a continuous update of their sensory information and knowledge bases.

Active Learning Self-Driving Cars

Adaptive importance sampling for seismic fragility curve estimation

no code yet • 9 Sep 2021

As part of Probabilistic Risk Assessment studies, it is necessary to study the fragility of mechanical and civil engineered structures when subjected to seismic loads.

Active Learning

AdjointNet: Constraining machine learning models with physics-based codes

no code yet • 8 Sep 2021

Results show that AdjointNet-based inversion can estimate process model parameters with reasonable accuracy.

Active Learning Physics-informed machine learning

Active Learning for Automated Visual Inspection of Manufactured Products

no code yet • 6 Sep 2021

Quality control is a key activity performed by manufacturing enterprises to ensure products meet quality standards and avoid potential damage to the brand's reputation.

Active Learning