Curriculum unlearning in humans and neural networks
cs.LG, q-bio.NC
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/licezhang/curriculum_
Terminology
Sources
- When Do Curricula Work?
- Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning
- Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
- Theory of Curriculum Learning, with Convex Loss Functions
- On The Power of Curriculum Learning in Training Deep Networks
- Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
- An Analytical Theory of Curriculum Learning in Teacher-Student Networks
- Early learning of the optimal constant solution in neural networks and humans
- Overcoming Simplicity Bias in Deep Networks using a Feature Sieve
- SGD on Neural Networks Learns Functions of Increasing Complexity
- On the Spectral Bias of Neural Networks
- Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
- Opening the Black Box of Deep Neural Networks via Information
- Abrupt and spontaneous strategy switches emerge in simple regularised neural networks
- Neural networks are a priori biased towards Boolean functions with low entropy
- Meta-Learned Models of Cognition
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis