BROWSE
Detail
Conference Paper
Dynamic Neural Thresholding on Mixed-Signal Neuromorphic Processors Enabled by Integrated Learning and Hardware Design
Cited - time in 
Share 
Share
- Authors
- Kyuseung Han, Kwang-Il Oh, Sukho Lee, Hyeonguk Jang, Jae-Jin Lee, Sooyoung Jang
- Issue Date
- 2026-04
- Citation
- Design, Automation & Test in Europe Conference (DATE) 2026, pp.1-7
- Publisher
- European Design and Automation Association
- Language
- English
- Type
- Conference Paper
- Abstract
- Spiking neural networks (SNNs) can improve inference accuracy through joint optimization of synaptic weights and neuronal thresholds. However, mixed signal neuromorphic processors, which are designed for energy efficiency using analog circuits, face practical limitations. In particular, digital to analog converters (DACs) often lack sufficient resolution to represent the large threshold values required by joint optimization. To address this issue, we propose a mixed signal neuromorphic processor architecture that shifts threshold control to digital logic. This approach removes the need for high-resolution DACs and allows dynamic threshold adjustment without modifying the analog neural core. We also propose a learning method tailored to this architecture. We evaluate the proposed design on five image classification benchmarks, measuring accuracy, latency, and energy consumption. The results show that our architecture consistently improves accuracy across benchmarks while incurring only minimal latency and energy overhead. This demonstrates that the proven benefits of joint weight and threshold learning can be realized in energy efficient analog hardware.
- Keyword
- neuromorphic processor, spiking neural network, SoC, mixed-signal, threshold
- KSP Keywords
- Digital logic, Dynamic Threshold, Energy efficiency, High resolution, Image Classification, Integrated learning, Joint optimization, Joint weight, Learning methods, Processor architecture, Synaptic weight