Nonlinear dynamics of localization in neural receptive fields

arXiv:2501.17284 · cs.LG · Submitted 2025-01-28 · Read on arXiv

cs.LG

Submitted: 2025-01-28

Updated: 2025-01-28

Code: https://github.com/leonlufkin/localization

Terminology

• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• Data Distributional Properties Drive Emergent In-Context Learning in Transformers
• On the Symmetries of Deep Learning Models and their Internal Representations
• Modelling the influence of data structure on learning in neural networks: the hidden manifold model
• Revisiting Self-Supervised Visual Representation Learning
• Understanding Neural Networks Through Deep Visualization
• Visualizing and Understanding Convolutional Networks

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