@inproceedings{6c7770154a80460a9a955a28f4629408,
title = "Systematic Design of Ring VCO-Based SNN - Translating Training Parameters to Circuits -",
abstract = "Spiking Neural Networks (SNNs) are a class of neural networks that mimic biological neurons and are more energy-efficient than conventional neural networks. The neuron model is the building block of an SNN, and many efficient hardware implementations of the neuron model have been proposed. This work aims to bridge the gap between the design of the neuron model and training SNNs with the neuron model. The work focuses on a ring oscillator-based neuron model, which realizes the leaky integrate-and-fire (LIF) neuron. The design of the ring oscillator-based neuron is discussed, and the neuron model is digitized using the bilinear transform to enable training. The trained network is used to classify the MNIST dataset with an accuracy of 97.35\%. The circuit parameters used for training the network are discussed, which can be used to build the circuit of the ring oscillator-based neuron.",
keywords = "Backpropagation, Bilinear Transform, Leaky Integrate-and-Fire, Ring Oscillator, Spiking Neural Networks",
author = "Sai Sanjeet and Sanchari Das and Chiang, \{Shiuh Hua Wood\} and Masahiro Fujita and Sahoo, \{Bibhu Datta\}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 67th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2024 ; Conference date: 11-08-2024 Through 14-08-2024",
year = "2024",
doi = "10.1109/MWSCAS60917.2024.10658910",
language = "English",
series = "Midwest Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1212--1216",
booktitle = "2024 IEEE 67th International Midwest Symposium on Circuits and Systems, MWSCAS 2024",
address = "United States",
}