Spiking Temporal Memory

Overview

This repository contains a detailed mathematical description and a reference implementation of the spiking Temporal Memory (sTM) model, originally developed by Bouhadjar et al. (2022). ... Various flavors of the model have been used in a number of follow-up studies (Bouhadjar et al. (2023a), Bouhadjar et al. (2023b), Siegel et al. (2023a), Siegel et al. (2023b), Bouhadjar et al. (2025)).

Model description

A detailed mathematical, implementation agnostic description of the model and its parameters is provided here.

Model implementations

• PyNEST

Repository contents

docs	model description (implementation agnostic)
PyNEST	PyNEST implementaton (python package)
PyNEST/src/spikingtemporalmemory	source code
PyNEST/examples	examples illustrating usage of the python package
PyNEST/tests	unit tests

References

Bouhadjar, Y., Wouters, D. J., Diesmann, M., & Tetzlaff, T. (2022). Sequence learning, prediction, and replay in networks of spiking neurons. PLOS Computational Biology, 18(6), e1010233.

Bouhadjar, Y., Wouters, D. J., Diesmann, M., & Tetzlaff, T. (2023). Coherent noise enables probabilistic sequence replay in spiking neuronal networks. PLOS Computational Biology, 19(5), e1010989.

Bouhadjar, Y., Siegel, S., Tetzlaff, T., Diesmann, M., Waser, R., & Wouters, D. J. (2023). Sequence learning in a spiking neuronal network with memristive synapses. Neuromorphic Computing and Engineering, 3(3), 034014.

Siegel, S., Bouhadjar, Y., Tetzlaff, T., Waser, R., Dittmann, R., & Wouters, D. J. (2023). System model of neuromorphic sequence learning on a memristive crossbar array. Neuromorphic Computing and Engineering, 3(2), 024002.

Siegel, S., Ziegler, T., Bouhadjar, Y., Tetzlaff, T., Waser, R., Dittmann, R., & Wouters, D. (2023, April). Demonstration of neuromorphic sequence learning on a memristive array. In Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference (pp. 108-114).

Bouhadjar Y., Lober M., Neftci E., Diesmann M., Tetzlaff T. (2025). Unsupervised continual learning of complex sequences in spiking neuronal networks. Proceedings of the International Conference on Neuromorphic Systems (ICONS'25)

Contact

• Younes Bouhadjar
• Melissa Lober
• Tom Tetzlaff

Contribute

We welcome contributions to the documentation and the code. For bug reports, feature requests, documentation improvements, or other issues, please create a GitHub issue.

License

The material in this repository is subject to different licenses:

• All material outside the PyNEST folder is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. For details, see here.

• The material inside the PyNEST folder is licensed under the GNU General Public License v3.0 or later. For details, see here.