Score: 1

SFATTI: Spiking FPGA Accelerator for Temporal Task-driven Inference -- A Case Study on MNIST

Published: July 4, 2025 | arXiv ID: 2507.10561v1

By: Alessio Caviglia , Filippo Marostica , Alessio Carpegna and more

Potential Business Impact:

Makes computers recognize handwriting faster and cheaper.

Business Areas:
Field-Programmable Gate Array (FPGA) Hardware

Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse nature, making them well-suited for low-power Field Programmable Gate Array (FPGA)-based deployment. This paper explores using the open-source Spiker+ framework to generate optimized SNNs accelerators for handwritten digit recognition on the MNIST dataset. Spiker+ enables high-level specification of network topologies, neuron models, and quantization, automatically generating deployable HDL. We evaluate multiple configurations and analyze trade-offs relevant to edge computing constraints.

Repos / Data Links

Page Count
6 pages

Category
Computer Science:
Neural and Evolutionary Computing