Eventax enables exact-gradient training of arbitrary ODE-defined spiking neuron models in JAX via differentiable ODE solvers integrated with event detection.
Fast and energy-efficient neuromorphic deep learning with first-spike times
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A timing-based backpropagation algorithm for multi-spike SNNs achieves ANN-comparable accuracy and identifies an optimal time constant for spike counts not seen in single-spike models.
citing papers explorer
-
Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX
Eventax enables exact-gradient training of arbitrary ODE-defined spiking neuron models in JAX via differentiable ODE solvers integrated with event detection.
-
Timing-Based Backpropagation in Spiking Neural Networks Without Single-Spike Restrictions
A timing-based backpropagation algorithm for multi-spike SNNs achieves ANN-comparable accuracy and identifies an optimal time constant for spike counts not seen in single-spike models.