snnTorch – Deep and online learning with spiking neural networks in Python.
snnTorch is based on the work presented in:
- J. K. Eshraghian, M. G. Ward, E. Neftci, X. Wang, G. Lenz, G. Dwivedi, M. Bennamoun, D. S. Jeong and W. D. Lu, “Training Spiking Neural Networks Using Lessons From Deep Learning”, arXiv preprint arXiv:2109.12894, Sept. 2021.[pdf]
Additional Resources:
SpikeGPT– A lightweight generative language model with pure binary, event-driven spiking activation units.
SpikeGPT is based on the work presented in:
- R. Zhu, Q. Zhao, J. K. Eshraghian, “SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks”, arXiv preprint arXiv:2302.13939. [arXiv]
OpenSpike – A fully open source spiking neural network accelerator based on OpenRAM, SkyWater130, and the OpenLane flow.
OpenSpike is based on the work presented in:
- F. Modaresi, M. Guthaus, J. K. Eshraghian, “OpenSpike: An OpenRAM SNN Accelerator”, 2023 IEEE Symposium on Circuits and Systems, Monterey, CA, USA, May 2023. [arXiv]
Quantized Spiking Neural Networks – Quantization-Aware Training in SNNs.
The original code was described in the following paper:
- J. K. Eshraghian, C. Lammie, M. R. Azghadi and W. D. Lu, “Navigating Local Minima in Quantized Spiking Neural Networks”, 2022 IEEE Artificial Intelligence Circuits and Systems Conference, Incheon, Korea, May 2022.[pdf]
Memristor-CMOS Ternary Logic Simulator – SPICE netlists of a memristor-CMOS ternary logic family.
The original code is described in the following paper:
-
X. Wang, P. Zhou, J.K. Eshraghian, C.-Y. Lin, H. H. C. Iu, T.-C. Chang, S.-M. Kang, “High-Density Memristor-CMOS Logic Family”, IEEE Transactions on Circuits and Systems I: Regular Papers, October 2020, doi: 10.1109/TCSI.2020.3027693.[pdf]
Artificial Retina Simulator – Retina simulator derived from a discrete neuronal network of retinal cell.
The original code was described in the following paper:
-
J. K. Eshraghian, S. Baek W. Thio, Y. Sandamirskaya, H.H.C. Iu and W. Lu, “A Real-Time Retinomorphic Simulator Using a Conductance-Based Discrete Neuronal Network”, 2020 IEEE Artificial Intelligence Circuits and Systems Conference, Milan, Italy, March 2020, pp. 79-83.[pdf]
Video-to-Spike Vision Simulator – Real-time video conversion into phototransduction mechanisms. The result is passed into the artificial retina simulator.
The original code was developed to interface with upper-limb prosthesis control in the following paper:
-
C. Arrow, J.K. Eshraghian, H. Wu, S. Baek, H. Iu and K. Nazarpour, “Prosthesis Control Using Spike-Rate Coding in the Retina Photoreceptor Cells”, 2021 IEEE International Symposium on Circuits and Systems, Daegu, South Korea, 2021.