Copertina

Do Neural Networks Lose Plasticity in a Gradually Changing World?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Tianhui, Mou, Lili
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
di: Hao, Yongchang, et al.
Pubblicazione: (2024)

Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks
di: Hao, Yongchang, et al.
Pubblicazione: (2024)

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
di: Hao, Yongchang, et al.
Pubblicazione: (2026)

Neural Network Plasticity and Loss Sharpness
di: Koster, Max, et al.
Pubblicazione: (2024)

Flora: Low-Rank Adapters Are Secretly Gradient Compressors
di: Hao, Yongchang, et al.
Pubblicazione: (2024)

iPINNER: An Iterative Physics-Informed Neural Network with Ensemble Kalman Filter
di: Lu, Binghang, et al.
Pubblicazione: (2025)

A Dual-View Approach to Classifying Radiology Reports by Co-Training
di: Han, Yutong, et al.
Pubblicazione: (2024)

Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing
di: Shayegh, Behzad, et al.
Pubblicazione: (2024)

Knowledge Distillation Must Account for What It Loses
di: Wang, Wenshuo
Pubblicazione: (2026)

The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift
di: Hong, Zhe
Pubblicazione: (2026)

Deep Spatio-Temporal Neural Network for Air Quality Reanalysis
di: Kheder, Ammar, et al.
Pubblicazione: (2025)

Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference
di: Schmitt, Marvin, et al.
Pubblicazione: (2023)

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
di: Shin, Baekrok, et al.
Pubblicazione: (2024)

Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs
di: Ailon, Nir, et al.
Pubblicazione: (2025)

Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value
di: Ma, Le, et al.
Pubblicazione: (2025)

Do Deep Neural Network Solutions Form a Star Domain?
di: Sonthalia, Ankit, et al.
Pubblicazione: (2024)

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
di: Joudaki, Amir, et al.
Pubblicazione: (2025)

Online Neural Networks for Change-Point Detection
di: Hushchyn, Mikhail, et al.
Pubblicazione: (2020)

Can We Understand Plasticity Through Neural Collapse?
di: Bonifazi, Guglielmo, et al.
Pubblicazione: (2024)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
di: Park, Sangyeon, et al.
Pubblicazione: (2025)

A Simple Baseline for Stable and Plastic Neural Networks
di: Künzel, Étienne, et al.
Pubblicazione: (2025)

Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation
di: Ma, Yao, et al.
Pubblicazione: (2024)

Reservoir Network with Structural Plasticity for Human Activity Recognition
di: Zyarah, Abdullah M., et al.
Pubblicazione: (2025)

COLD: Causal reasOning in cLosed Daily activities
di: Joshi, Abhinav, et al.
Pubblicazione: (2024)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
di: Zhu, Yunqin, et al.
Pubblicazione: (2026)

Integrating Attention-Enhanced LSTM and Particle Swarm Optimization for Dynamic Pricing and Replenishment Strategies in Fresh Food Supermarkets
di: Liu, Xianchen, et al.
Pubblicazione: (2025)

Let the Quantum Creep In: Designing Quantum Neural Network Models by Gradually Swapping Out Classical Components
di: Wang, Peiyong, et al.
Pubblicazione: (2024)

Contextual Thompson Sampling via Generation of Missing Data
di: Zhang, Kelly W., et al.
Pubblicazione: (2025)

Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
di: Kim, Hyunwoo, et al.
Pubblicazione: (2025)

Ensemble Distillation for Unsupervised Constituency Parsing
di: Shayegh, Behzad, et al.
Pubblicazione: (2023)

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
di: Bechler-Speicher, Maya, et al.
Pubblicazione: (2025)

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
di: Wang, Shengyuan, et al.
Pubblicazione: (2025)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
di: Lee, Hojoon, et al.
Pubblicazione: (2024)

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
di: Yu, Zony, et al.
Pubblicazione: (2025)

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
di: Omura, Motoki, et al.
Pubblicazione: (2025)

Plasticity as the Mirror of Empowerment
di: Abel, David, et al.
Pubblicazione: (2025)

Do Transformer World Models Give Better Policy Gradients?
di: Ma, Michel, et al.
Pubblicazione: (2024)

Fed-Credit: Robust Federated Learning with Credibility Management
di: Chen, Jiayan, et al.
Pubblicazione: (2024)

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
di: Ma, Qian, et al.
Pubblicazione: (2024)

Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
di: Shayegh, Behzad, et al.
Pubblicazione: (2024)