Results 21 to 30 of about 2,374,745 (297)
Algorithm Selection for Deep Active Learning with Imbalanced Datasets [PDF]
Neural Information Processing Systems, 2023 Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can ...
Jifan Zhang +3 more
semanticscholar +1 more source
Uncertainty-Aware Learning against Label Noise on Imbalanced Datasets [PDF]
AAAI Conference on Artificial Intelligence, 2022 Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks.Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean and noisy ...
Yingsong Huang +4 more
semanticscholar +1 more source
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets [PDF]
Neural Information Processing Systems, 2023 Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning techniques such ...
Zhang-Wei Hong +8 more
semanticscholar +1 more source
Over-sampling imbalanced datasets using the Covariance Matrix [PDF]
EAI Endorsed Transactions on Energy Web, 2020 INTRODUCTION: Nowadays, many machine learning tasks involve learning from imbalanced datasets,leading to the miss-classification of the minority class. One of the state-of-the-art approaches to ”solve” thisproblem at the data level is Synthetic Minority ...
Ireimis Leguen-deVarona +3 more
doaj +1 more source
RSG: A Simple but Effective Module for Learning Imbalanced Datasets [PDF]
Computer Vision and Pattern Recognition, 2021 Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem.
Jianfeng Wang +4 more
semanticscholar +1 more source
Active Learning for Imbalanced Datasets
2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020 Active learning increases the effectiveness of labeling when only subsets of unlabeled datasets can be processed manually. To our knowledge, existing algorithms are designed under the assumption that datasets are balanced. However, many real-life datasets are actually imbalanced and we propose two adaptations of active learning to tackle imbalance ...
Aggarwal, Umang +2 more
openaire +2 more sources
Data-Centric Optimization Approach for Small, Imbalanced Datasets
Journal of Information and Organizational Sciences, 2023 Data-centric is a newly explored concept, where the attention is given to data optimization methodologies and techniques to improve model performance, rather than focusing on machine learning models and hyperparameter tunning.
Vladislav Tanov
doaj +1 more source
IDPP: Imbalanced Datasets Pipelines in Pyrus
, 2023 We showcase and demonstrate IDPP, a Pyrus-based tool that offers a collection of pipelines for the analysis of imbalanced datasets. Like Pyrus, IDPP is a web-based, low-code/no-code graphical modelling environment for ML and data analytics applications. On a case study from the medical domain, we solve the challenge of re-using AI/ML models that do not
Amandeep Singh, Olga Minguett
openaire +2 more sources
Distribution-sensitive learning for imbalanced datasets [PDF]
2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2013 Many real-world face and gesture datasets are by nature imbalanced across classes. Conventional statistical learning models (e.g., SVM, HMM, CRY), however, are sensitive to imbalanced datasets. In this paper we show how an imbalanced dataset affects the performance of a standard learning algorithm, and propose a distribution-sensitive prior to deal ...
Song, Yale +2 more
openaire +3 more sources
Boosting methods for multi-class imbalanced data classification: an experimental review
Journal of Big Data, 2020 Since canonical machine learning algorithms assume that the dataset has equal number of samples in each class, binary classification became a very challenging task to discriminate the minority class samples efficiently in imbalanced datasets.
Jafar Tanha +4 more
doaj +1 more source