Results 11 to 20 of about 235,048 (260)
A survey on semi-supervised learning [PDF]
Machine Learning, 2019 AbstractSemi-supervised learning is the branch of machine learning concerned with using labelled as well as unlabelled data to perform certain learning tasks. Conceptually situated between supervised and unsupervised learning, it permits harnessing the large amounts of unlabelled data available in many use cases in combination with typically smaller ...
Jesper E Van Engelen +2 more
exaly +3 more sources
A Survey on Deep Semi-Supervised Learning
IEEE Transactions on Knowledge and Data Engineering, 2023 Deep semi-supervised learning is a fast-growing field with a range of practical applications. This paper provides a comprehensive survey on both fundamentals and recent advances in deep semi-supervised learning methods from perspectives of model design and unsupervised loss functions.
Xiangli Yang, Zixing Song, Irwin KING
exaly +3 more sources
SemiBoost: Boosting for Semi-Supervised Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009 Semi-supervised learning has attracted a significant amount of attention in pattern recognition and machine learning. Most previous studies have focused on designing special algorithms to effectively exploit the unlabeled data in conjunction with labeled data. Our goal is to improve the classification accuracy of any given supervised learning algorithm
Rong Jin, Anil K Jain
exaly +3 more sources
Semi-Supervised Apprenticeship Learning
, 2012 International audienceIn apprenticeship learning we aim to learn a good policy by observing the behavior of an expert or a set of experts. In particular, we consider the case where the expert acts so as to maximize an unknown reward function defined as a
Valko, Michal +2 more
core +3 more sources
Semi-supervised learning [PDF]
Machine Learning, 1989 The distribution-independent model of (supervised) concept learning due to Valiant (1984) is extended to that of semi-supervised learning (ss-learning), in which a collection of disjoint concepts is to be simultaneously learned with only partial information concerning concept membership available to the learning algorithm.
Raymond A. Board, Leonard Pitt
openaire +2 more sources
Learning to Learn in a Semi-supervised Fashion [PDF]
, 2020 To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like in person re-identification or image retrieval.
Yun-Chun Chen +2 more
openaire +2 more sources
Human Semi‐Supervised Learning [PDF]
Topics in Cognitive Science, 2013 AbstractMost empirical work in human categorization has studied learning in either fully supervised or fully unsupervised scenarios. Most real‐world learning scenarios, however, are semi‐supervised: Learners receive a great deal of unlabeled information from the world, coupled with occasional experiences in which items are directly labeled by a ...
Bryan R. Gibson +2 more
openaire +2 more sources
Contrastive Semi-Supervised Learning for ASR [PDF]
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021 Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer. Inspired by the successes of contrastive representation learning for computer vision and speech applications, and ...
Alex Xiao +2 more
openaire +2 more sources
Semi-supervised Learning for Anomalous Trajectory Detection [PDF]
, 2008 A novel learning framework is proposed for anomalous behaviour detection in a video surveillance scenario, so that a classifier which distinguishes between normal and anomalous behaviour patterns can be incrementally trained with the assistance of a ...
Fisher, Bob +3 more
core +1 more source
Semi-Supervised Learning for Image Classification using Compact Networks in the BioMedical Context [PDF]
, 2022 Background and objectives: The development of mobile and on the edge appli-cations that embed deep convolutional neural models has the potential to revolutionisebiomedicine.
Díaz-Pinto, Andrés +5 more
core