Research

Tachyon: Parallelizing Discrete Spiking Neural Networks via Associative Operators & Bounded Discretization

Spiking Neural Networks (SNNs) represent a promising frontier for high-efficiency, event-driven artificial intelligence. However, training deep spiking architectures on modern accelerator clusters has long been constrained by two fundamental computational walls: the $O(T)$ temporal unrolling bottleneck in discrete time steps and the $O(N_{out}{N}_{in})$ activation memory explosion in continuous-time event processing.

Read paper →