Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/shoaibdipu/Neural_Succession
Terminology
Sources
- The Effect of Task Ordering in Continual Learning
- On Tiny Episodic Memories in Continual Learning
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- Gradient Descent Happens in a Tiny Subspace
- Toward Understanding Catastrophic Forgetting in Continual Learning
- Progressive Neural Networks
- Three scenarios for continual learning
- Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks