Curriculum learning
The DOI matches its Crossref record; 35 of the 40 references it cites were found in a registry or an index.
Abstract
Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them "curriculum learning". In the context of recent research studying the difficulty of training in the presence of non-convex training criteria (for deep deterministic and stochastic neural networks), we explore curriculum learning in various set-ups. The experiments show that significant improvements in generalization can be achieved. We hypothesize that curriculum learning has both an effect on the speed of convergence of the training process to a minimum and, in the case of non-convex criteria, on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of non-convex functions).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Moreover, the lack of acoustical signals could even account for spatial disorientation 91,92.”
From The impact of multisensory integration and perceptual load in virtual reality settings on performance, workload and presence (2021) · cites this paper as [92]
In the citing paper
“This suggests that curriculum-style learning (Bengio et al., 2009), where simpler or archetypal problems are presented first to build a repository of valid heuristics, may potentially bootstrap performance.”
From Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory (2025) · cites this paper as Bengio et al., 2009
Citations
Cites
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
Self-citationExtracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
Self-citationA unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 6×
“In Collobert and Weston (2008), the main objective is to learn an embedding for the words as a side-e.ect of learning to compute this score.”
BackgroundMethodInfluentialSelf-citationLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Self-citationGreedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
Self-citationA Neural Probabilistic Language Model
Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C., Jaz, K., Hofmann, T., Poggio, T., & Shawe-Taylor, J. S. (2000) · Cited by 3,479
Self-citationLearning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 8×
“The idea of training a learning machine with a curriculum can be traced back at least to Elman (1993).”
BackgroundMethodInfluentialRestricted Boltzmann machines for collaborative filtering
Salakhutdinov, R., Mnih, A., & Hinton, G. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273596 · Cited by 1,885
Research works printed but not linked: 3
- 10.5555/89603 · doi:10.5555/89603
- 10.5555/866740 · doi:10.5555/866740
- 10.5555/525571 · doi:10.5555/525571
Cited by
Items 4,801–4,900 of 5,240
Ye, B., Xia, J., Wan, X., Wu, M., & Chiba, S. (2026) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.70264
“Moreover, curriculum learning could pro - vide a suitable training strategy for multi-barcode data with differ - ent sample coverages, as this approach trains a machine learning model from easier data to harder data (Bengio et al., 2009; Wang et al., 2022 ).”
Singh, M., Challagundla, J., Raina, S., & Jarsania, J. (2026) · Conference on Multimedia Modeling · doi:10.1007/978-981-95-6950-2_40
“Unlike typical easy-to-hard curriculum learning [1, 39], we adopt a hard-first approach, which we find highly effective when paired with synthetic CoT rationales.”
Deepfake Identification Strategies for Secure Cyberspace Engagement
Goswami, S., Saha, S., & Happy (2025) · International Conference on Intelligent Systems for Cybersecurity (ISCS) · doi:10.1109/iscs69371.2025.11385930 · Cited by 1
“Curriculum Learning: During training, a gradual introduction of increasingly challenging examples has proved to be advantageous in terms of robustness [40].”
Sharma, S., Hooper, A. J., Hogg, D., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6253807
Curriculum Learning in Medical Image Analysis
Meghatria, R., Gaceb, D., & Touazi, F. (2025) · doi:10.1109/aiia68273.2025.11383658
“Curriculum strategies can improve sample efficiency by starting the training with simpler, clearly healthy images then gradually introducing more complex cases, which improves model robustness and allows models to achieve high performance with limited number of labeled examples [7], [27].”
InfluentialYousefimehr, B., Ghatee, M., & Razavi‐Far, R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6262580
Beyond Memorization: Generalizable Snake AI with DDQN in Cluttered Environments
Wesley, P. J., & Raj, A. S. A. (2025) · IEEE International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC) · doi:10.1109/isssc66652.2025.11388853
“Future research will focus on advanced DRL methods such as PPO or SAC, dynamic obstacle scenarios, and curriculum learning to further strengthen spatial reasoning and adaptability [10].”
Diverse Subset Selection via Norm-Based Sampling and Orthogonality
Bar, N., & Giryes, R. (2026) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2026.3666822 · Cited by 1
“Finally, curriculum learning and data cartography aim to order training examples based on their importance or difficulty, facilitating optimization rather than directly reducing data volume [36], [37].”
PCL-AED: progressive acoustic event detection based on contrastive learning
Chen, Y., & Huang, J. (2026) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-026-00447-4
Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation
Li, F., Xu, Q., Bao, S., Han, B., Yang, Z., & Huang, Q. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00057 · Cited by 8
“To mitigate the risk of overfitting, we apply a curriculum learning [4] strategy, positioning these easy (low intra-class variance) identities at the beginning of the training dataset, followed by harder (high intra-class variance) identities [2, 3] from the cleaned HSFace set.”
da Silva, V. L., Tomás, R., Cores, F., & Giné, F. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00343
“[2], this paradigm organizes the training process by presenting easier examples first and gradually increasing difficulty.”
Sangthaworn, T., & Sakulkueakulsuk, B. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11377445
“While learning rates decay [9], exploration rates decrease [10], and curricula adapt task difficulty [11], [12], the foundational bipedal methods like DeepMimic [13] and AMP [14] maintain constant reward weights throughout training.”
AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation
Shen, L., Edalati, A., Li, X., Meyer, B. H., Gross, W. J., & Clark, J. J. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00656
Yolo driven computer vision framework for paddy disease
Kumar, S., Kumar, S., & Nandan, D. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-00945-6 · Cited by 1
Xia, Y., Liu, W., Sun, X., Yang, J., Tong, Y., & Zhang, Y. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11523-8
Wang, Z., Zhang, J., & Zhang, C. (2026) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2026.3660337
“The training process follows a two-stage structure, where the stage decomposition is heuristically designed according to the coordination requirements of swarm exploration tasks, and is further enhanced through curriculum learning [13], network augmentation [14], and reward shaping [15].”
Kaci, R., Lezzar, F., & Mili, S. E. (2025) · International Conference on Research in Computing at Feminine (RIF) · doi:10.1109/rif68108.2025.11406849
“Curriculum learning is a training paradigm in which a model is exposed to samples in a meaningful order, typically starting with easier instances and gradually progressing to more difficult ones [23].”
Jeffery, Z., Bramantoro, A., Siau, N. Z., & Noorfatimah, S. (2025) · International Conference on Applied Computational Intelligence in Information Systems (ACIIS) · doi:10.1109/aciis66255.2025.11402941
“CL provides a structured training approach in which an agent progresses from simple to increasingly complex tasks, enhancing training stability and convergence [12], [13].”
A fine-grained image classification method based on MGCN-FGIC
Zhang, C., Zhang, Q., Ren, J., Xue, T., & Fu, J. (2026) · The Visual Computer · doi:10.1007/s00371-026-04393-2
“To enable the model to concentrate resources on overcoming difficult tasks, a Dynamic Hard Example Mining (DHEM) mechanism is designed by drawing on the ideas of Curriculum Learning [33] and Focal Loss [34].”
Fernandes, M. R., Gupta, V., Parmar, K. H., Johnvictor, A. C., & Prem Sankar, N. (2026) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids69108.2026.11407703
Self-training for graph class imbalance via global and local topology fusion
Zhou, R., Shao, C., Zheng, S., & Yu, H. (2026) · Connection Science · doi:10.1080/09540091.2026.2633885
Improving Neural Architecture Search by Minimizing Worst-Case Validation Loss
Zhang, H., Du, X., Zhang, R., & Xie, P.-T. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3670777
“Some CL works [2], [53], [61], [65], [81] use task-specific prior knowledge to measure hardness of examples, which are not generalizable across a variety of tasks.”
Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
Tu, Y., Zhong, Z., Li, Y., & Zhao, H. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02745-y · Cited by 5
Exploiting Meta-Learning-Based Poisoning Attacks for Graph Link Prediction
Li, M., Zhuang, D., Chen, K., et al. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402598
“The weight for epoch i is calculated as: • Linear-based Weighting: Inspired by curriculum learning [27], where models learn more effectively when data is introduced from simple to complex, our linear weighting adopts a similar philosophy.”
SRAS: A Lightweight Reinforcement Learning-Based Document Selector for Edge-Native RAG Pipelines
Rajiv Chaitanya, M. (2025) · International Conference on Intelligent Computing and Systems at the Edge (ICEdge) · doi:10.1109/icedge67252.2025.11412749
Sayed, A. E., Roshan, R. G., Muthiah, S., & Muralidhar, N. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401733
“One technique for improving model performance in low-data regimes is curriculum learning (CL) [28].”
A Dataset Establishment Method for Wind Turbine Wake and a Data-Driven Model of Wake Prediction
Tang, Q., Wu, Y., Li, C., Duan, P., Wu, J., & Lyu, J. (2026) · Energies · doi:10.3390/en19051385
Mamba-based Deep Reference Frame Generation for Inter Prediction Enhancement in NNVC
Zhang, W., Ma, W., Fu, N., et al. (2025) · Picture Coding Symposium · doi:10.1109/pcs65673.2025.11417505
“In addition, similar to the principles of curriculum learning proposed in [14], this staged exposure facilitates smoother model optimization and leads to more stable training as shown in Figure 3 in Section III-C.”
Li, X., Zhang, H., Yang, S., Wang, Y. Y., Liu, X., & Lu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7072-0_35
LightMotion: A Lightweight Motion Prediction Model with Spatial Attention and Progressive Learning
Aditya, W., Chen, W.-H., Lin, Y.-C., & Yang, T. J. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423658
“Inspired by [16], we introduce a simple-to-complex progressive learning strategy to address these challenges.”
InfluentialTriplet Contrastive Learning for Multiobject Tracking in Satellite Videos
Zhang, W., Wang, R., Liu, J., Li, Y., & Xiao, L. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3675693
“Thus, we adopt the training strategy based on curriculum learning [48], [49] to train TCLTracker.”
Collision-Aware UAV Delivery via Learning-Based Autonomous ControlPreprint
Barros, I. D. S., de Oliveira, F. M. C., Bittencourt, L. F., & Kamienski, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6442693 · Cited by 1
Binary and Tri-state Finger Actions for Robot Learning Robust In-hand Manipulation SkillsPreprint
Bhattacharya, R., Akash, M. I., Adwani, N., Lu, L., & Wang, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6438449
MXPose: Multiplex Interactive Learning for Multi-View 3D Human Pose EstimationPreprint
Guan, Z., Zhang, W., Liu, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6446245
Curriculum-based Reinforcement Learning for Flexibility Evaluation in Buildings
Payonga, L. R., Madani, H., & Stefan, M. (2026) · doi:10.1109/pesim67009.2026.11438317
“While more formal and theoretical CL frameworks exist, such as that by Narvekar et al. [6] and those reviewed by Soviany et al. [7] , this work adopts a straightforward application of the general CL idea introduced by Bengio et al. [8].”
Refer-ASV: Referring Multi-Object Tracking in Autonomous Surface Vehicle Navigation Scenes
Xue, B., Yu, Q., Ding, K., Wang, Y., Xiang, S., & Pan, C. (2026) · Journal of Imaging · doi:10.3390/jimaging12040145 · Cited by 1
Wang, W., Zhu, A., Hu, T., Wang, S., & Dai, Y. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3674228
“CL, proposed by Bengio et al. [21], has rapidly become an important research direction in the field of machine learning [36].”
Jia, X. (2026) · IEEE International Conference on Power, Electronics and Green Energy (ICPEGE) · doi:10.1109/icpege67691.2026.11451328
“Owing to these advantages, GRPO has been successfully applied to optimize multimodal large language models, with notable successes such as Visual-R1 demonstrating superior performance over standard supervised fine-tuning (SFT) and vanilla PPO[17] in grounding and visual reasoning tasks.”
Overcoming Data Loss in Wearable Disease Detection with GAN-Based Imputation
Wallner, J. F., Berbuir, S., Birner, L., Dendorfer, A., Panthi, B., Rahnsch, B., Muma, J. O., Munga, S., Obor, D., Bärnighausen, T., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02518-4 · Cited by 2
“Toimprove robustness under increasing levels of missingness, we employed curriculum learning 46 : training began with masking rates of 40% and gradually increased to 70% over successive epochs, mimicking pro-gressivelymoredif fi cultimputationscenarios.”
AudioAuth: A Dual-Watermarking Framework for Robust Audio Integrity and Source Attribution
Pujari, A., & Rattani, A. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3679274
“By first learning clean embedding and then gradually introducing distortions, the model develops stable imperceptible representations before confronting aggressive perturbations, following curriculum-learning principles [45].”
Yang, Y., Wen, Y., Zhu, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8420-8_10
Kodumagulla, P. (2026) · Research Square · doi:10.21203/rs.3.rs-9286871/v1
Fang, Y.-H., Lo, T.-H., Sung, Y., et al. (2025) · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru65441.2025.11434693
“…end, we design thorough experiments using the TEEMI dataset and pro-pose Speech-First Multimodal Training (SFMT), a curriculum learning approach [16] that progressively transitions from speech foundations to cross-modal integration, achieving an absolute improvement of 4% in terms of the…”
Deep Learning for Advanced Microscopy
Ouyang, W. (2018) · theses.fr (ABES) · doi:10.70675/a4542914z1070z4bb1z87cfzaaa97f8ab733
Rethinking the Design of Sequence-to-Sequence Models for Efficient Machine Translation
Elbayad, M. (2020) · theses.fr (ABES) · doi:10.70675/97c82c7ez86c5z4bdbza801z12232614c776 · Cited by 2
Forestier, S. (2019) · theses.fr (ABES) · doi:10.70675/abd58967z79d0z4df2zbe94z307821e9b628 · Cited by 7
Clinical Gait Assessment using 3D data
Khokhlova, M. (2018) · theses.fr (ABES) · doi:10.70675/7771c4f5za99dz427bz91e8za8039299996a
Minimum complexity principle for knowledge transfer in artificial learning
Murena, P.-A. (2018) · theses.fr (ABES) · doi:10.70675/7c739dcfze3a3z4b37zb67ez833e8fdbcf92 · Cited by 1
Active learning and input space analysis for deep networks
Ducoffe, M. (2018) · theses.fr (ABES) · doi:10.70675/e68c8520z28aaz4696z9a6azdb6f15330f8e · Cited by 2
Granger, N. (2019) · theses.fr (ABES) · doi:10.70675/9f7530bez3094z498fzbaf7zbfac62e25c00
Sun, Z., Li, W., Shi, G., & Schonfeld, P. M. (2026) · ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part A Civil Engineering · doi:10.1061/ajrua6.rueng-1850
Sur le rôle de l’être humain dans le dialogue humain/machine
Barlier, M. (2018) · theses.fr (ABES) · doi:10.70675/6593c9f6za16ez4d62z9b6fzc1bca5e50df4
MultiScale Knowledge Distillation
Liu, S., Yao, Z., & Li, J. (2026) · Machine Learning · doi:10.1007/s10994-026-07035-9
“Inspired by the curriculum learning method (Bengio et al., 2009; Faber et al., 2024 ), the student network first learns relatively simple small-scale knowledge and gradually incorporates larger-scale knowledge in the later stages.”
du Terrail, J. O. (2018) · theses.fr (ABES) · doi:10.70675/083d206az0a4ez4480z866ez53e9de431d15 · Cited by 1
Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera
Pinard, C. (2019) · theses.fr (ABES) · doi:10.70675/14bf1a7dz78a9z4170zbfacz9b660a96e7db · Cited by 2
Light Field Image and Video Compression
Bakir, N. (2020) · theses.fr (ABES) · doi:10.70675/6ec279f3zeb31z4faeza746zacfc954ef21b
Lesort, T. (2020) · theses.fr (ABES) · doi:10.70675/e714c94ezb6d9z4adbz9daaz60088df88f5f · Cited by 3
Communication in Robot Learning : usage of the Combined Task and Social Channelfor Action Learning
Bied, M. (2022) · theses.fr (ABES) · doi:10.70675/23a2fc96z1dd1z4481z91eezcbd6b801ec95
Epigenetic learning of autonomous behaviours in a society of agents
Suro, F. (2020) · theses.fr (ABES) · doi:10.70675/42a85f76z3d93z4e73zb5f1zd4e8649f5dde · Cited by 1
Vers un apprentissage protéiforme : accomoder les changements de signature des agents artificiels.
Bonnici, I. (2021) · theses.fr (ABES) · doi:10.70675/590f2d18z3876z4b8bz8b0aze027f97ef684
Méta-apprentissage par renforcement pour le contrôle adaptatif
Jaafra, Y. (2020) · theses.fr (ABES) · doi:10.70675/4a9b4240zabb1z45abz8446z5a014f63e1c0
Cendre, R. (2021) · theses.fr (ABES) · doi:10.70675/92fd40b8z03c6z4261z88dez1d4b85e069a4 · Cited by 1
Du signal au concept : réseaux de neurones profonds appliqués à la compréhension de la parole
Caubrière, A. (2021) · theses.fr (ABES) · doi:10.70675/06618edcz398dz4d15zb4e4z448661057453
Multi-domain Neural Machine Translation
Pham, M.-Q. (2021) · theses.fr (ABES) · doi:10.70675/17e2ca68z8662z4bb9zb875zac511563f5c6 · Cited by 23
Automatic Curriculum Learning for Developmental Machine Learners
Portelas, R. (2022) · theses.fr (ABES) · doi:10.70675/947677c7z2ec1z4b61zbae3z6f358c02b050
Gonthier, N. (2021) · theses.fr (ABES) · doi:10.70675/9abc66b4zca61z423bz85dcz07b849b15209 · Cited by 1
Emulation and prediction of cosmic web simulations through deep learning
Ullmo, M. (2022) · theses.fr (ABES) · doi:10.70675/573f6397z1449z43b8z9139z7de47c7a67c5
Learning increasingly complex skills through deep reinforcement learning using intrinsic motivation
Aubret, A. (2021) · theses.fr (ABES) · doi:10.70675/6f863351zdd37z4da4z9fa2z5ceed27ddd07 · Cited by 1
Echo-aware signal processing for audio scene analysis
Carlo, D. D. (2020) · theses.fr (ABES) · doi:10.70675/5e2ef467za1f4z40a8z8c60zda82f29cdcb1 · Cited by 5
Naini, A. R., & Busso, C. (2026) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2026.3680785
“Curriculum learning (CL) is an approach where the training data is strategically ordered from easier to progressively more challenging examples, enhancing model convergence and generalization [31].”
Hunter drones : drones cooperation for tracking an intruder drone
de Souza, C. (2021) · theses.fr (ABES) · doi:10.70675/f7b6e3e9zf6d5z415eza8b5z42a0cc79e919 · Cited by 3
Few-Shot Intent Classification in User-Generated Short Texts : Application to Conversational Agents
Dopierre, T. (2021) · theses.fr (ABES) · doi:10.70675/ce4875adzcf6ez4960z908dz7dcd0ea70205 · Cited by 1
SkyFind: A Large-Scale Benchmark Unveiling Referring Expression Comprehension for UAV
Wang, K., Wu, G., Fu, X., Wang, X., Liu, K., Lu, X. B., Ge, C., Zhai, W., & Zhang, J. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3681112 · Cited by 8
“Based on this, the proposed two-stage framework can be interpreted through the lens of the continuation method [83], [84].”
Intrinsically Motivated and Interactive Reinforcement Learning : a Developmental Approach
Fournier, P. (2019) · theses.fr (ABES) · doi:10.70675/525d96caz1d44z4f9cz86bfzb69a83bf40b5 · Cited by 1
Modelling patterns of search behaviours from user interactions
Lugo, L. (2021) · theses.fr (ABES) · doi:10.70675/0110331fzd69cz422cz95d6zc392f2c6e643 · Cited by 2
Novello, P. (2022) · theses.fr (ABES) · doi:10.70675/fde62335z8ca3z478cz8ddcz466a6a243163 · Cited by 1
Mitriakov, A. (2022) · theses.fr (ABES) · doi:10.70675/394f136ez684dz4cf8z8ff6zd40334b097c1
Deep learning methods for music style transfer
Cífka, O. (2021) · theses.fr (ABES) · doi:10.70675/fb591beeza958z4897z936dz180fad412ad9 · Cited by 1
Boualili, L. (2022) · theses.fr (ABES) · doi:10.70675/29d19654z89d4z4f44z85efz0add721cac69
Challenges of Real Life Few-Shot Image Classification
Bennequin, E. (2023) · theses.fr (ABES) · doi:10.70675/5e095960z69ebz4e66za7aczd02b259e695b · Cited by 2
Rodrigues, H. D. N. (2023) · theses.fr (ABES) · doi:10.70675/a0210e97ze844z4f11z93e1zb64db1b962c8 · Cited by 2
Towards lighter and faster deep neural networks with parameter pruning
Hubens, N. (2022) · theses.fr (ABES) · doi:10.70675/c018d7baz3aa3z43b2z9f61z0d9bb05ff94e
Deep Learning in Neuroimaging for Multiple Sclerosis
Kamraoui, R. A. (2023) · theses.fr (ABES) · doi:10.70675/faacb09ez7b3fz49c2z9de1zaf3e812da25f
Search-based and supervised text generation
Fabre, B. (2022) · theses.fr (ABES) · doi:10.70675/6379e915z5ae2z4cfez8b10z2e04e43ba265
Biquality learning : from weakly supervised learning to distribution shifts
Nodet, P. (2023) · theses.fr (ABES) · doi:10.70675/41d22fb9z3d38z4a64z9a3cz4a385058629c
Data series indexes that learn
Wang, Q. (2023) · theses.fr (ABES) · doi:10.70675/725340b5zb6f2z4ff7z80c1z40f61818aa27
Τοwards Εnd-tο-end Ηandwritten Dοcument Recοgnitiοn
Coquenet, D. (2022) · theses.fr (ABES) · doi:10.70675/72509686z0497z4c89zaddaz87231e389c26
Neural graph-to-text generation with euclidean and riemannian graph encoding
Montella, S. (2023) · theses.fr (ABES) · doi:10.70675/b0563a9fz0ff1z4daaza710za9e4d3ed4301
Analysis and Recommendation Methods for Class-Incremental Learning
Feillet, E. (2024) · theses.fr (ABES) · doi:10.70675/6a2efeadzbf0cz4783z8c67z0d5e86d6cb48
Deep Learning for Partially Observed Dynamical Systems
Monsel, T. (2024) · theses.fr (ABES) · doi:10.70675/55aa8297z3a6fz4b05zb01bz208bafb66fe8 · Cited by 1
Human-Machine Co-Learning : interactive curriculum generation for the acquisition of motor skills
Sungeelee, V. (2024) · theses.fr (ABES) · doi:10.70675/0fd09746zc195z4bbdzb16ezfe80df8dce3f
Improving Cooperation in Multi-agent Deep Reinforcement Learning for Mobile Robotics
Toquebiau, M. (2024) · theses.fr (ABES) · doi:10.70675/3385d0bbzc66cz4fceza9e0z8696ff61ff4e
Unsupervised image analysis by synthesis
Monnier, T. (2023) · theses.fr (ABES) · doi:10.70675/be82a99cz2b90z4712z8162ze20de1394feb
Simulation Of Diverse Human Play-Styles In Video Games : A Reinforcement Learning Approach
de Woillemont, P. L. P. (2023) · theses.fr (ABES) · doi:10.70675/51b3c6d7z2e51z47fcz8d7azf1106953ba36 · Cited by 1
Graph Neural Networks for fluid mechanics : data-assimilation and optimization
Quattromini, M. (2024) · theses.fr (ABES) · doi:10.70675/78a75e36z1cbdz4ff0z8bc9z5379e6b8c9b5 · Cited by 2
Metadata
- Authors
- Bengio, Y., Louradour, J., Collobert, R., & Weston, J.
- Affiliations
- Université de Montréal (CA)
- NEC Laboratories America, Princeton, NJ
- ORCID
- Bengio, Yoshua
- Venue
- Proceedings of the 26th Annual International Conference on Machine Learning
- Publisher
- ACM
- Published
- 2009-06-14
- Pages
- 41-48
- OpenAlex
- W2296073425
- Semantic Scholar
- 8de174ab5419b9d3127695405efd079808e956e8
- Cited by
- 5,366
- References
- 40
- Citations by year
- 2026: 526 · 2025: 636 · 2024: 551 · 2023: 591 · 2022: 536 · 2021: 711 · 2020: 565 · 2019: 442 · 2018: 293 · 2017: 198 · 2016: 103 · 2015: 63 · 2014: 41 · 2013: 40 · 2012: 33
- FWCI
- 16.17
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning (publishedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- Funders
- Canadian Institute for Advanced Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- curriculum learning, training order, non-convex optimization, deep neural network, stochastic neural networks, deterministic neural networks, generalization, convergence rate, numerical continuation, global optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.