Score: 0

Implementation and Analysis of Thermometer Encoding in DWN FPGA Accelerators

Published: December 17, 2025 | arXiv ID: 2512.15251v1

By: Michael Mecik, Martin Kumm

Potential Business Impact:

Makes smart computer chips use less space.

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

Fully parallel neural network accelerators on field-programmable gate arrays (FPGAs) offer high throughput for latency-critical applications but face hardware resource constraints. Weightless neural networks (WNNs) efficiently replace arithmetic with logic-based inference. Differential weightless neural networks (DWN) further optimize resource usage by learning connections between encoders and LUT layers via gradient-based training. However, DWNs rely on thermometer encoding, and the associated hardware cost has not been fully evaluated. We present a DWN hardware generator that includes thermometer encoding explicitly. Experiments on the Jet Substructure Classification (JSC) task show that encoding can increase LUT usage by up to 3.20$\times$, dominating costs in small networks and highlighting the need for encoding-aware hardware design in DWN accelerators.

Country of Origin
🇩🇪 Germany

Page Count
5 pages

Category
Computer Science:
Hardware Architecture