paper-with-me

홈 › Papers

Do Neural Networks Lose Plasticity in a Gradually Changing World?

2026-02-09 · Tianhui Liu, Lili Mou arxiv

Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks gradually losing the ability to learn new tasks. However, existing plasticity research largely relies on benchmarks with abrupt task transitions, without examining whether the abruptness itself contributes to the observed plasticity loss. In this paper, we investigate the role of transition abruptness by simulating gradually changing environments through input/output interpolation and task sampling. We perform theoretical and empirical analysis, showing that the severity of plasticity loss is closely tied to the abruptness of task transitions, and can be substantially reduced when the environment changes gradually.

📄 PDF Abstract BibTeX arXiv:2602.09234

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networks

2022-11-23 · Bing Han, Feifei Zhao, Yi Zeng, Guobin Shen

Developmental plasticity plays a prominent role in shaping the brain's structure during ongoing learning in response to dynamically changing environments. However, the existing network compression methods for deep artifi…

Deep Reinforcement Learning with Plasticity Injection

2023-05-24 · NeurIPS 2023 11

A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phen…

Computational EfficiencyDeep Reinforcement LearningDiagnosticreinforcement-learning+2

Balancing Plasticity and Stability with Fast and Slow Successor Features

2026-05-25 · Raymond Chua, Doina Precup, Blake Richards arxiv

A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Prior studies introduce non-stationarity through abrupt shif…

Reinforcement LearningContinual Learning

Loss of Plasticity in Continual Deep Reinforcement Learning

2023-03-13 · Zaheer Abbas, Rosie Zhao, Joseph Modayil, Adam White 외

The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL) approaches under varying degrees of non…

Atari GamesContinual LearningDeep Reinforcement Learningreinforcement-learning+2

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

2023-08-23 · Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li 외

The evolution of the human brain has led to the development of complex synaptic plasticity, enabling dynamic adaptation to a constantly evolving world. This progress inspires our exploration into a new paradigm for Spiki…