Imagen de Portada

Toward industrial use of continual learning : new metrics proposal for class incremental learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Abbas, Konaté Mohamed, Yao, Anne-Françoise, Chateau, Thierry, Bouges, Pierre
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards stable training of parallel continual learning
por: Yuepan, Li, et al.
Publicado: (2024)

Recommendation of data-free class-incremental learning algorithms by simulating future data
por: Feillet, Eva, et al.
Publicado: (2024)

Interactive incremental learning of generalizable skills with local trajectory modulation
por: Knauer, Markus, et al.
Publicado: (2024)

Local vs Global continual learning
por: Lanzillotta, Giulia, et al.
Publicado: (2024)

A step toward a reinforcement learning de novo genome assembler
por: Padovani, Kleber, et al.
Publicado: (2021)

Review learning: Real world validation of privacy preserving continual learning across medical institutions
por: Yoo, Jaesung, et al.
Publicado: (2022)

Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning
por: Zhao, Hanyang, et al.
Publicado: (2024)

Context selectivity with dynamic availability enables lifelong continual learning
por: Barry, Martin, et al.
Publicado: (2023)

Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift
por: Guo, Liangxuan, et al.
Publicado: (2023)

LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression
por: Zeghlache, Rachid, et al.
Publicado: (2024)

TinySubNets: An efficient and low capacity continual learning strategy
por: Pietroń, Marcin, et al.
Publicado: (2024)

Forager: a lightweight testbed for continual learning with partial observability in RL
por: Tang, Steven, et al.
Publicado: (2026)

Task diversity produces systematic transfer but inhibits continual reinforcement learning
por: Seth, Purab, et al.
Publicado: (2026)

Soup to go: mitigating forgetting during continual learning with model averaging
por: Kleiman, Anat, et al.
Publicado: (2025)

FastODT: A tree-based framework for efficient continual learning
por: Bretsko, Daniel, et al.
Publicado: (2026)

A theoretical framework for self-supervised contrastive learning for continuous dependent data
por: Marusov, Alexander, et al.
Publicado: (2025)

Towards efficient representation identification in supervised learning
por: Ahuja, Kartik, et al.
Publicado: (2022)

Towards a theory of out-of-distribution learning
por: Dey, Jayanta, et al.
Publicado: (2021)

Self-supervised learning on gene expression data
por: Dradjat, Kevin, et al.
Publicado: (2025)

Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification
por: Peire, Nina, et al.
Publicado: (2026)

Don't throw the baby out with the bathwater: How and why deep learning for ARC
por: Cole, Jack, et al.
Publicado: (2025)

Application of linear regression and quasi-Newton methods to the deep reinforcement learning in continuous action cases
por: Komatsu, Hisato
Publicado: (2025)

Deep reinforcement learning for weakly coupled MDP's with continuous actions
por: Robledo, Francisco, et al.
Publicado: (2024)

Toward efficient resource utilization at edge nodes in federated learning
por: Alawadi, Sadi, et al.
Publicado: (2023)

MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
por: Bal-Ghaoui, Mohamed, et al.
Publicado: (2025)

Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold
por: Chaudhuri, Anupam, et al.
Publicado: (2024)

Normalization and effective learning rates in reinforcement learning
por: Lyle, Clare, et al.
Publicado: (2024)

Practical machine learning is learning on small samples
por: Sapir, Marina
Publicado: (2025)

Preventing overfitting in deep learning using differential privacy
por: Khatri, Alizishaan Anwar Hussein
Publicado: (2026)

Exemplar-condensed Federated Class-incremental Learning
por: Sun, Rui, et al.
Publicado: (2024)

Curriculum reinforcement learning with measurable task representation learning
por: Wen, Yongyan, et al.
Publicado: (2026)

Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning
por: Wang, Yaqing, et al.
Publicado: (2023)

Training instability in deep learning follows low-dimensional dynamical principles
por: Zhang, Zhipeng, et al.
Publicado: (2026)

Predicting life satisfaction using machine learning and explainable AI
por: Khan, Alif Elham, et al.
Publicado: (2025)

PROTECT: Protein circadian time prediction using unsupervised learning
por: Ogholbake, Aram Ansary, et al.
Publicado: (2025)

Class-incremental Learning for Time Series: Benchmark and Evaluation
por: Qiao, Zhongzheng, et al.
Publicado: (2024)

Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations
por: Mandyam, Aishwarya, et al.
Publicado: (2021)

Similarity-based context aware continual learning for spiking neural networks
por: Han, Bing, et al.
Publicado: (2024)

Does learning the right latent variables necessarily improve in-context learning?
por: Mittal, Sarthak, et al.
Publicado: (2024)

Stochastic Q-learning for Large Discrete Action Spaces
por: Fourati, Fares, et al.
Publicado: (2024)