中文
相关论文

相关论文: AdaER: An Adaptive Experience Replay Approach for …

200 篇论文

In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based…

机器学习 · 计算机科学 2023-10-13 Zihao Xu , Xuan Tang , Yufei Shi , Jianfeng Zhang , Jian Yang , Mingsong Chen , Xian Wei

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

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

机器学习 · 计算机科学 2020-12-09 Timothée Lesort

Session-based recommendation has received growing attention recently due to the increasing privacy concern. Despite the recent success of neural session-based recommenders, they are typically developed in an offline manner using a static…

机器学习 · 计算机科学 2020-07-24 Fei Mi , Xiaoyu Lin , Boi Faltings

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

机器学习 · 计算机科学 2020-10-13 Pietro Buzzega , Matteo Boschini , Angelo Porrello , Simone Calderara

In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such…

机器学习 · 计算机科学 2021-03-03 Arslan Chaudhry , Albert Gordo , Puneet K. Dokania , Philip Torr , David Lopez-Paz

Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal-based strategy, which optimizes the model with current…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Tao Zhuo , Zhiyong Cheng , Zan Gao , Hehe Fan , Mohan Kankanhalli

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

机器学习 · 计算机科学 2023-08-04 Quanziang Wang , Renzhen Wang , Yuexiang Li , Dong Wei , Kai Ma , Yefeng Zheng , Deyu Meng

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

计算机视觉与模式识别 · 计算机科学 2025-01-27 Haoran Chen , Micah Goldblum , Zuxuan Wu , Yu-Gang Jiang

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and…

机器学习 · 计算机科学 2026-03-04 Zhanwang Liu , Yuting Li , Haoyuan Gao , Yexin Li , Linghe Kong , Lichao Sun , Weiran Huang

With the capacity of continual learning, humans can continuously acquire knowledge throughout their lifespan. However, computational systems are not, in general, capable of learning tasks sequentially. This long-standing challenge for deep…

机器学习 · 计算机科学 2022-08-05 Qihan Yang , Fan Feng , Rosa Chan

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay…

机器学习 · 计算机科学 2022-05-11 Elahe Arani , Fahad Sarfraz , Bahram Zonooz

Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in…

机器学习 · 计算机科学 2024-08-27 Monica Millunzi , Lorenzo Bonicelli , Angelo Porrello , Jacopo Credi , Petter N. Kolm , Simone Calderara

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

机器学习 · 计算机科学 2021-02-04 Mirza Ramicic , Andrea Bonarini

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

机器学习 · 计算机科学 2022-04-26 Lucas Caccia , Rahaf Aljundi , Nader Asadi , Tinne Tuytelaars , Joelle Pineau , Eugene Belilovsky

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

机器学习 · 计算机科学 2022-05-03 Lucas Caccia , Rahaf Aljundi , Nader Asadi , Tinne Tuytelaars , Joelle Pineau , Eugene Belilovsky

Conventional replay-based approaches to continual learning (CL) require, for each learning phase with new data, the replay of samples representing all of the previously learned knowledge in order to avoid catastrophic forgetting. Since the…

机器学习 · 计算机科学 2023-03-24 Alexander Krawczyk , Alexander Gepperth

Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual…

机器学习 · 计算机科学 2021-07-19 Yujiang He , Bernhard Sick

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

计算与语言 · 计算机科学 2021-07-27 Nithin Holla , Pushkar Mishra , Helen Yannakoudakis , Ekaterina Shutova

Automatic speech recognition (ASR) technologies today are primarily optimized for given datasets; thus, any changes in the application environment (e.g., acoustic conditions or topic domains) may inevitably degrade the performance. We can…

计算与语言 · 计算机科学 2021-07-05 Heng-Jui Chang , Hung-yi Lee , Lin-shan Lee
‹ 上一页 1 2 3 10 下一页 ›