Multi-timescale conductance spiking networks deliver a gradient-trainable, sparse neuron model with diverse firing regimes that outperforms LIF and AdLIF baselines on Mackey-Glass regression.
Predicting chaotic time series
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Deep-Koopman-KANDy recovers symbolic Koopman dictionaries post-training by replacing the encoder and decoder with KANs and applying a level-set construction with chain-rule gradients, achieving high recall on Lorenz and expected behavior on other maps.
FEG-Pro estimates finite-horizon forecast-error growth slopes from scalar time series via kNN multi-horizon forecasting as proxies for largest Lyapunov exponents, while extracting additional profile descriptors.
citing papers explorer
-
Multi-Timescale Conductance Spiking Networks: A Sparse, Gradient-Trainable Framework with Rich Firing Dynamics for Enhanced Temporal Processing
Multi-timescale conductance spiking networks deliver a gradient-trainable, sparse neuron model with diverse firing regimes that outperforms LIF and AdLIF baselines on Mackey-Glass regression.
-
Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
Deep-Koopman-KANDy recovers symbolic Koopman dictionaries post-training by replacing the encoder and decoder with KANs and applying a level-set construction with chain-rule gradients, achieving high recall on Lorenz and expected behavior on other maps.
-
FEG-Pro: Forecast-Error Growth Profiling for Finite-Horizon Instability Analysis of Nonlinear Time Series
FEG-Pro estimates finite-horizon forecast-error growth slopes from scalar time series via kNN multi-horizon forecasting as proxies for largest Lyapunov exponents, while extracting additional profile descriptors.