Sumit Bam Shrestha — accepted AI-conference papers

2025

Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity

Alessandro Pierro, Steven Abreu, Jonathan Timcheck, Philipp Stratmann, Andreas Wild, Sumit Bam Shrestha

ICML 2025poster

Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in resource-constrained environments requires hardware-aware optimizat…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Efficient Video and Audio Processing with Loihi 2

Sumit Bam Shrestha, Jonathan Timcheck, Edward Paxon Frady, Leobardo Campos-Macias, Mike Davies

ICASSP 2024accepted

Loihi 2 is an asynchronous, brain-inspired research processor that generalizes several fundamental elements of neuromorphic architecture, such as stateful neuron models communicating with event-driven spikes, in order to address limitations of the first generation Loihi. Here we explore and characte…

Cited by 0 Source ↗Scholar ↗

2020

Event-Based Angular Velocity Regression with Spiking Networks

Mathias Gehrig, Sumit Bam Shrestha, Daniel Mouritzen, Davide Scaramuzza

ICRA 2020poster

Spiking Neural Networks (SNNs) are bio-inspired networks that process information conveyed as temporal spikes rather than numeric values. An example of a sensor providing such data is the event-camera. It only produces an event when a pixel reports a significant brightness change. Similarly, the spi…

Cited by 118 Source ↗code ↗Scholar ↗

2018

SLAYER: Spike Layer Error Reassignment in Time

Sumit Bam Shrestha, Garrick Orchard

NeurIPS 2018poster

Configuring deep Spiking Neural Networks (SNNs) is an exciting research avenue for low power spike event based computation. However, the spike generation function is non-differentiable and therefore not directly compatible with the standard error backpropagation algorithm. In this paper, we introduc…

Cited by 1009 Source ↗PDF ↗code ↗Scholar ↗