Similar Items: ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data
- Adaptive Domain Decomposition Physics-Informed Neural Networks for Traffic State Estimation with Sparse Sensor Data
- Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
- Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle
- Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks
- TabSurv: Adapting Modern Tabular Neural Networks to Survival Analysis
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior