中文
相关论文

相关论文: Forget Forgetting: Continual Learning in a World o…

200 篇论文

While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing sequential data with recurrent neural networks (RNNs) is…

Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including…

机器学习 · 计算机科学 2024-03-21 Zhenyi Wang , Yan Li , Li Shen , Heng Huang

Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously…

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…

机器学习 · 计算机科学 2022-04-12 Johannes von Oswald , Christian Henning , Benjamin F. Grewe , João Sacramento

The majority of online continual learning (CL) advocates single-epoch training and imposes restrictions on the size of replay memory. However, single-epoch training would incur a different amount of computations per CL algorithm, and the…

机器学习 · 计算机科学 2025-03-18 Minhyuk Seo , Hyunseo Koh , Jonghyun Choi

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

机器学习 · 计算机科学 2023-09-04 Nicolas Michel , Giovanni Chierchia , Romain Negrel , Jean-François Bercher , Toshihiko Yamasaki

One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However,…

机器学习 · 计算机科学 2024-04-16 Seungyub Han , Yeongmo Kim , Taehyun Cho , Jungwoo Lee

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the…

机器学习 · 计算机科学 2024-07-31 Weichen Lin , Jiaxiang Chen , Ruomin Huang , Hu Ding

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…

机器学习 · 计算机科学 2021-01-19 Ammar Shaker , Shujian Yu , Francesco Alesiani

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and network expansion for balancing model stability and plasticity,…

机器学习 · 计算机科学 2024-01-18 Depeng Li , Tianqi Wang , Junwei Chen , Qining Ren , Kenji Kawaguchi , Zhigang Zeng

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…

机器学习 · 计算机科学 2020-12-09 Arslan Chaudhry , Naeemullah Khan , Puneet K. Dokania , Philip H. S. Torr

Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.…

机器学习 · 计算机科学 2026-04-27 Liangzu Peng , Uday Kiran Reddy Tadipatri , Ziqing Xu , Eric Eaton , René Vidal

Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to…

机器学习 · 计算机科学 2021-10-29 Maciej Wołczyk , Michał Zając , Razvan Pascanu , Łukasz Kuciński , Piotr Miłoś

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

机器学习 · 计算机科学 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of neural networks. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is…

机器学习 · 计算机科学 2023-04-11 Haiyan Zhao , Tianyi Zhou , Guodong Long , Jing Jiang , Chengqi Zhang

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robustness has decomposed…

机器学习 · 计算机科学 2023-07-04 Hikmat Khan , Nidhal C. Bouaynaya , Ghulam Rasool

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. We focus on continual text classification under the class-incremental setting. Recent CL studies have identified…

计算与语言 · 计算机科学 2023-10-11 Yifan Song , Peiyi Wang , Weimin Xiong , Dawei Zhu , Tianyu Liu , Zhifang Sui , Sujian Li

Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…

机器学习 · 计算机科学 2024-08-15 Anna Vettoruzzo , Joaquin Vanschoren , Mohamed-Rafik Bouguelia , Thorsteinn Rögnvaldsson

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

机器学习 · 计算机科学 2023-10-11 Jinyung Hong , Theodore P. Pavlic

Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in…

机器学习 · 计算机科学 2023-03-21 Kamil Faber , Dominik Zurek , Marcin Pietron , Nathalie Japkowicz , Antonio Vergari , Roberto Corizzo