Fetching the paper…
Reading the bibliography…
Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data, which imitates the meaningful learning order in human curricula.
Reinforcement today
B. Skinner · 1958
Earlier work this paper cites.
Limitations on input as a basis for neural organization and perceptual development: A preliminary theoretical statement
G. Turkewitz, · 1982
Earlier work this paper cites.
Training and tracking in robotics
O. Selfridge, · 1985
Earlier work this paper cites.
Maturational constraints on language learning
E. Newport · 1990
Earlier work this paper cites.
Curious model-building control systems
J. Schmidhuber · 1991
Earlier work this paper cites.
Learning and development in neural networks: The importance of starting small
J. L Elman · 1993
Earlier work this paper cites.
Neural network learning control of robot manipulators using gradually increasing task difficulty
T. Sanger · 1994
Earlier work this paper cites.
Experiments with a new boosting algorithm
Y. Freund, · 1996
Earlier work this paper cites.
Language acquisition in the absence of explicit negative evidence: How important is starting small?
D. Rohde, · 1999
Earlier work this paper cites.
Optimization transfer using surrogate objective functions
K. Lange, · 2000
Earlier work this paper cites.
Smote: synthetic minority over-sampling technique
N. Chawla, · 2002
Earlier work this paper cites.
A day of great illumination: Bf skinner’s discovery of shaping
G. Peterson · 2004
Earlier work this paper cites.
Model selection and estimation in regression with grouped variables
M. Yuan, · 2006
Earlier work this paper cites.
Curriculum learning
Y. Bengio, · 2009
Earlier work this paper cites.
Flexible shaping: How learning in small steps helps
K. A Krueger, · 2009
Earlier work this paper cites.
A survey on transfer learning
S. Pan, · 2009
Earlier work this paper cites.
Active learning literature survey
B. Settles · 2009
Earlier work this paper cites.
Self-paced learning for latent variable models
M. Kumar, · 2010
Earlier work this paper cites.
Intelligent selection of language model training data
R. Moore, · 2010
Earlier work this paper cites.
A review of instance selection methods
J. Olvera-López, · 2010
Earlier work this paper cites.
From baby steps to leapfrog: How “less is more” in unsupervised dependency parsing
V. Spitkovsky, · 2010
Earlier work this paper cites.
Learning specific-class segmentation from diverse data
M. Kumar, · 2011
Earlier work this paper cites.
Learning the easy things first: Self-paced visual category discovery
Y. Lee, · 2011
Earlier work this paper cites.
On the effectiveness of self-paced learning
J. Tullis, · 2011
Earlier work this paper cites.
Numerical continuation methods: an introduction
E. L Allgower, · 2012
Earlier work this paper cites.
Shifting weights: Adapting object detectors from image to video
K. Tang, · 2012
Earlier work this paper cites.
Self-paced dictionary learning for image classification
Y. Tang, · 2012
Earlier work this paper cites.
Learning with noisy labels
N. Natarajan, · 2013
Earlier work this paper cites.
Evolving culture versus local minima
Y. Bengio · 2014
Earlier work this paper cites.
Easy samples first: Self-paced reranking for zero-example multimedia search
L Jiang, · 2014
Earlier work this paper cites.
Self-paced learning with diversity
L Jiang, · 2014
Earlier work this paper cites.
Exclusive feature learning on arbitrary structures via l_1,2-norm
D. Kong, · 2014
Earlier work this paper cites.
Training deep neural networks on noisy labels with bootstrapping
S. Reed, · 2014
Earlier work this paper cites.
Learning to execute
W. Zaremba, · 2014
Earlier work this paper cites.
Variance reduction in sgd by distributed importance sampling
G. Alain, · 2015
Earlier work this paper cites.
Curriculum learning with deep convolutional neural networks, 2015
V. Avramova · 2015
Earlier work this paper cites.
Scheduled sampling for sequence prediction with recurrent neural networks
S. Bengio, · 2015
Earlier work this paper cites.
Webly supervised learning of convolutional networks
X. Chen, · 2015
Earlier work this paper cites.
Self-paced curriculum learning
L Jiang, · 2015
Earlier work this paper cites.
Online batch selection for faster training of neural networks
I. Loshchilov, · 2015
Earlier work this paper cites.
Curriculum learning of multiple tasks
A. Pentina, · 2015
Earlier work this paper cites.
Multi-view self-paced learning for clustering
C. Xu, · 2015
Earlier work this paper cites.
A self-paced multiple-instance learning framework for co-saliency detection
D. Zhang, · 2015
Earlier work this paper cites.
Self-paced learning for matrix factorization
Q. Zhao, · 2015
Earlier work this paper cites.
Visualizing and understanding curriculum learning for long short-term memory networks
V. Cirik, · 2016
Earlier work this paper cites.
Self-paced learning: an implicit regularization perspective
Y. Fan, · 2016
Earlier work this paper cites.
Training deep neural-networks using a noise adaptation layer
J. Goldberger, · 2016
Earlier work this paper cites.
Multi-modal curriculum learning for semi-supervised image classification
C. Gong, · 2016
Earlier work this paper cites.
Why curriculum learning & self-paced learning work in big/noisy data: A theoretical perspective
T. Gong, · 2016
Earlier work this paper cites.
Adaptive sampling for sgd by exploiting side information
S. Gopal · 2016
Cited alongside, same era.
Self-paced multi-task learning
C. Li, · 2016
Cited alongside, same era.
Multi-objective self-paced learning
H. Li, · 2016
Cited alongside, same era.
Self-paced cross-modal subspace matching
J. Liang, · 2016
Cited alongside, same era.
Learning to detect concepts from webly-labeled video data
J. Liang, · 2016
Cited alongside, same era.
Self-paced boost learning for classification
T. Pi, · 2016
Cited alongside, same era.
Training region-based object detectors with online hard example mining
A. Shrivastava, · 2016
Learning to teach with dynamic loss functions
L. Wu, · 2018
Later among the works it cites.
An empirical exploration of curriculum learning for neural machine translation
X. Zhang, · 2018
Later among the works it cites.
Deep self-paced learning for person re-identification
S. Zhou, · 2018
Later among the works it cites.
Minimax curriculum learning: Machine teaching with desirable difficulties and scheduled diversity
T. Zhou, · 2018
Later among the works it cites.
A brief introduction to weakly supervised learning
Z. Zhou · 2018
Later among the works it cites.
Pseudo-labeling curriculum for unsupervised domain adaptation
J. Choi, · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Learning the curriculum with bayesian optimization for task-specific word representation learning
Y. Tsvetkov, · 2016
Cited alongside, same era.
How hard can it be? estimating the difficulty of visual search in an image
R. Tudor Ionescu, · 2016
Cited alongside, same era.
Stc: A simple to complex framework for weakly-supervised semantic segmentation
Y. Wei, · 2016
Cited alongside, same era.
A curriculum learning method for improved noise robustness in automatic speech recognition
S. Braun, · 2017
Cited alongside, same era.
Active bias: Training more accurate neural networks by emphasizing high variance samples
H. Chang, · 2017
Cited alongside, same era.
Balanced self-paced learning for generative adversarial clustering network
K. Ghasedi, · 2019
Later among the works it cites.
Multi-modal curriculum learning over graphs
C. Gong, · 2019
Later among the works it cites.
On the power of curriculum learning in training deep networks
G. Hacohen, · 2019
Later among the works it cites.
Weakly-supervised learning of category-specific 3d object shapes
J. Han, · 2019
Later among the works it cites.
Self-attention enhanced cnns and collaborative curriculum learning for distantly supervised relation extraction
Y. Huang, · 2019
Later among the works it cites.
Medical-based deep curriculum learning for improved fracture classification
A. Jiménez-Sánchez, · 2019
Later among the works it cites.
Self-paced contextual reinforcement learning
P. Klink, · 2019
Later among the works it cites.
Reinforcement learning based curriculum optimization for neural machine translation
G. Kumar, · 2019
Later among the works it cites.
Teacher-student curriculum learning
T. Matiisen, · 2019
Later among the works it cites.
Curriculum learning strategies for ir: An empirical study on conversation response ranking
G. Penha, · 2019
Later among the works it cites.
Competence-based curriculum learning for neural machine translation
E. Platanios, · 2019
Later among the works it cites.
Data parameters: A new family of parameters for learning a differentiable curriculum
S. Saxena, · 2019
Later among the works it cites.
Transferable curriculum for weakly-supervised domain adaptation
Y. Shu, · 2019
Later among the works it cites.
Self-paced active learning: Query the right thing at the right time
Y. Tang, · 2019
Later among the works it cites.
Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives
Y. Tay, · 2019
Later among the works it cites.
Dynamically composing domain-data selection with clean-data selection by” co-curricular learning” for neural machine translation
W. Wang, · 2019
Later among the works it cites.
Dynamic curriculum learning for imbalanced data classification
Y. Wang, · 2019
Later among the works it cites.
Adversarial examples: Attacks and defenses for deep learning
X. Yuan, · 2019
Later among the works it cites.
Learning object detectors with semi-annotated weak labels
D. Zhang, · 2019
Later among the works it cites.
Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework
D. Zhang, · 2019
Later among the works it cites.
Curriculum learning for domain adaptation in neural machine translation
X. Zhang, · 2019
Later among the works it cites.
Student-teacher curriculum learning via reinforcement learning: Predicting hospital inpatient admission location
R. El-Bouri, · 2020
Closest in time.
Breaking the curse of space explosion: Towards efficient nas with curriculum search
Y. Guo, · 2020
Closest in time.
Meta-learning in neural networks: A survey
T. Hospedales, · 2020
Closest in time.
Norm-based curriculum learning for neural machine translation
X. Liu, · 2020
Closest in time.
Curriculum learning for reinforcement learning domains: A framework and survey
S. Narvekar, · 2020
Closest in time.
Automatic curriculum learning for deep rl: A short survey
R. Portelas, · 2020
Closest in time.
Meta self-paced learning
J. Shu, · 2020
Closest in time.
Curriculum by smoothing
S. Sinha, · 2020
Closest in time.
Image difficulty curriculum for generative adversarial networks (cugan)
P. Soviany, · 2020
Closest in time.
Curriculum pre-training for end-to-end speech translation
C. Wang, · 2020
Closest in time.
Learning a multi-domain curriculum for neural machine translation
W. Wang, · 2020
Closest in time.
Optimizing data usage via differentiable rewards
X. Wang, · 2020
Closest in time.
Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification
L. Xiang, · 2020
Closest in time.
Curriculum learning for natural language understanding
B. Xu, · 2020
Closest in time.
Self-paced learning for k-means clustering algorithm
H. Yu, · 2020
Closest in time.
Synthesizing supervision for learning deep saliency network without human annotation
D. Zhang, · 2020
Closest in time.
Few-cost salient object detection with adversarial-paced learning
D. Zhang, · 2020
Closest in time.
Reinforced curriculum learning on pre-trained neural machine translation models
M. Zhao, · 2020
Closest in time.
Unsupervised feature selection by self-paced learning regularization
W. Zheng, · 2020
Closest in time.
Curriculum learning by dynamic instance hardness
T. Zhou, · 2020
Closest in time.
Uncertainty-aware curriculum learning for neural machine translation
Y. Zhou, · 2020
Closest in time.
A continual learning survey: Defying forgetting in classification tasks
M. Delange, · 2021
Closest in time.