plasticity
Plasticity in AI often refers to the ability of a model or neural network to adapt and update its weights based on new experiences or data, similar to the adaptability seen in biological systems, which can enhance learning and generalization.
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
- Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
- Federated Continual Learning via Orchestrating Multi-Scale Expertise
- Gradient-Guided Epsilon Constraint Method for Online Continual Learning
- Learning Multi-Source and Robust Representations for Continual Learning
- Plasticity as the Mirror of Empowerment
- Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
- Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
- Temporal-Difference Variational Continual Learning