Learning infinite context windows in recurrent architectures via spatial neural computing
cs.LG, cs.SY, eess.SY, q-bio.NC
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: 12 pages, 4 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- A Spatiotemporal Perspective on Dynamical Computation in Neural Information Processing Systems
- A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
- Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
- Higher Order Recurrent Neural Networks
- Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks