SNNtrainer3D: Training Spiking Neural Networks Using a User-Friendly Application with 3D Architecture Visualization Capabilities
Source abstract
Abstract
Spiking Neural Networks have gained significant attention due to their potential for energy efficiency and biological plausibility. However, the reduced number of user-friendly tools for designing, training, and visualizing Spiking Neural Networks hinders widespread adoption. This paper presents the SNNtrainer3D v1.0.0, a novel software application that addresses these challenges. The application provides an intuitive interface for designing Spiking Neural Networks architectures, with features such as dynamic architecture editing, allowing users to add, remove, and edit hidden layers in real-time. A key innovation is the integration of Three.js for three-dimensional visualization of the network structure, enabling users to inspect connections and weights and facilitating a deeper understanding of the model’s behavior. The application supports training on the Modified National Institute of Standards and Technology dataset and allows the downloading of trained weights for further use. Moreover, it lays the groundwork for future integration with physical memristor technology, positioning it as a crucial tool for advancing neuromorphic computing research. The advantages of the development process, technology stack, and visualization are discussed. The SNNtrainer3D represents a significant step in making Spiking Neural Networks more accessible, understandable, and easier for Artificial Intelligence researchers and practitioners.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural dynamics and brain function
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Print and Media Technology, Chemnitz University of Technology, Reichenhainer Straße 70, 09126 Chemnitz, Germany
Funding
German Federal Ministry of Education and Research (BMBF)
References (58)
Show source-provided references
1. He, J., Li, Y., Liu, Y., Chen, J., Wang, C., Song, R., and Li, Y. (2022, January 5–9). The development of Spiking Neural Network: A Review. Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO), Jinghong, China.10.1109/ROBIO55434.2022.10012028 ↗
2. Dorogyy, Y., and Kolisnichenko, V. (2016, January 23–26). Designing spiking neural networks. Proceedings of the 13th International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science (TCSET), Lviv, Ukraine.10.1109/TCSET.2016.7451989 ↗
3. Attention Spiking Neural Networks10.1109/TPAMI.2023.3241201 ↗
4. Abiyev, R.H., Kaynak, O., and Oniz, Y. (2012, January 11–14). Spiking neural networks for identification and control of dynamic plants. Proceedings of the 2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Kaohsiung, Taiwan.10.1109/AIM.2012.6265983 ↗
5. Honzík, V., and Mouček, R. (2021, January 9–12). Spiking Neural Networks for Classification of Brain-Computer Interface and Image Data. Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA.10.1109/BIBM52615.2021.9669864 ↗
6. El Arrassi, A., Gebregiorgis, A., El Haddadi, A., and Hamdioui, S. (2022, January 3–5). Energy-Efficient SNN Implementation Using RRAM-Based Computation In-Memory (CIM). Proceedings of the IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC), Patras, Greece.10.1109/VLSI-SoC54400.2022.9939654 ↗
7. Spiking Neural Networks for Visual Place Recognition Via Weighted Neuronal Assignments10.1109/LRA.2022.3149030 ↗
8. Yamazaki, K., Vo-Ho, V.-K., Bulsara, D., and Le, N. (2022). Spiking Neural Networks and Their Applications: A Review. Brain Sci., 12.10.3390/brainsci12070863 ↗
9. Pietrzak, P., Szczęsny, S., Huderek, D., and Przyborowski, Ł. (2023). Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities. Sensors, 23.10.3390/s23063037 ↗
10. Temporal dendritic heterogeneity incorporated with spiking neural networks for learning multi-timescale dynamics10.1038/s41467-023-44614-z ↗
11. Pfeiffer, M., and Pfeil, T. (2018). Deep Learning with Spiking Neurons: Opportunities and Challenges. Front. Neurosci., 12.10.3389/fnins.2018.00774 ↗
12. Opportunities for neuromorphic computing algorithms and applications10.1038/s43588-021-00184-y ↗
13. Visual explanations from spiking neural networks using inter-spike intervals10.1038/s41598-021-98448-0 ↗
14. Shen, G., Zhao, D., Li, T., Li, J., and Zeng, Y. (2023). Is Conventional SNN Really Efficient? A Perspective from Network Quantization. arXiv.
15. Sanaullah Koravuna, S., Rückert, U., and Jungeblut, T. (2022). SNNs Model Analyzing and Visualizing Experimentation Using RAVSim. Engineering Applications of Neural Networks, Springer. EANN 2022. Communications in Computer and Information Science.10.1007/978-3-031-08223-8_4 ↗
16. Evaluation of Spiking Neural Nets-Based Image Classification Using the Runtime Simulator RAVSim10.1142/S0129065723500442 ↗
17. SWsnn: A Novel Simulator for Spiking Neural Networks10.1089/cmb.2023.0098 ↗
18. (2024, June 10). Three.js—JavaScript 3D Library. Available online: https://threejs.org.
19. (2024, June 10). Neuromorphic for AI Computing and Sensing: Disruptive Technologies Are Here!. Available online: https://www.yolegroup.com/press-release/neuromorphic-for-ai-computing-and-sensing-disruptive-technologies-are-here/.
20. Bekolay, T., Bergstra, J., Hunsberger, E., DeWolf, T., Stewart, T.C., Rasmussen, D., Choo, X., Voelker, A.R., and Eliasmith, C. (2014). Nengo: A Python tool for building large-scale functional brain models. Front. Neuroinform., 7.10.3389/fninf.2013.00048 ↗
21. PyNEST: A convenient interface to the NEST simulator
22. Brian 2, an intuitive and efficient neural simulator10.7554/eLife.47314 ↗
23. Thorbergsson, P.T., Jorntell, H., Bengtsson, F., Garwicz, M., Schouenborg, J., and Johansson, A.J. (2009, January 3–6). Spike library based simulator for extracellular single unit neuronal signals. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, USA.10.1109/IEMBS.2009.5333847 ↗
24. Pecevski, D., Kappel, D., and Jonke, Z. (2014). NEVESIM: Event-driven neural simulation framework with a Python interface. Front. Neuroinform., 8.10.3389/fninf.2014.00070 ↗
25. Hazan, H., Saunders, D.J., Khan, H., Patel, D., Sanghavi, D.T., Siegelmann, H.T., and Kozma, R. (2018). BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python. Front. Neuroinform., 12.10.3389/fninf.2018.00089 ↗
26. SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence10.1126/sciadv.adi1480 ↗
27. Training Spiking Neural Networks Using Lessons from Deep Learning10.1109/JPROC.2023.3308088 ↗
28. Pehle, C.-G., and Pedersen, J.E. (2021). Norse—A Deep Learning Library for Spiking Neural Networks, Version 0.0.5, Zenodo.
29. Lava Software Framework (2024, June 10). A Software Framework for Neuromorphic Computing. Available online: http://lava-nc.org.
30. Sheik, S., Lenz, G., Bauer, F., and Kuepelioglu, N. (2023). SINABS: A Simple Pytorch Based SNN Library Specialised for Speck, Version 1.2.9, Zenodo.
31. (2024, June 10). Rockpool. Available online: https://gitlab.com/synsense/rockpool.
32. Niedermeier, L., Chen, K., Xing, J., Das, A., Kopsick, J., Scott, E., Sutton, N., Weber, K., Dutt, N., and Krichmar, J.L. (2022, January 18–23). CARLsim 6: An Open Source Library for Large-Scale, Biologically Detailed Spiking Neural Network Simulation. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy.10.1109/IJCNN55064.2022.9892644 ↗
33. Heckel, K.M., and Nowotny, T. (2024). Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks. arXiv.
34. NESIM-RT: A real-time distributed spiking neural network simulator10.1016/j.softx.2023.101349 ↗
35. Gemo, E., Spiga, S., and Brivio, S. (2024). SHIP: A computational framework for simulating and validating novel technologies in hardware spiking neural networks. Front. Neurosci., 17.10.3389/fnins.2023.1270090 ↗
36. Federated learning with spiking neural networks10.1109/TSP.2021.3121632 ↗
37. Comprehensive analytic performance assessment and k-means based multicast routing algorithm and architecture for 3d-noc of spiking neurons10.1145/3340963 ↗
38. Adaptive federated learning in resource constrained edge computing systems10.1109/JSAC.2019.2904348 ↗
39. Federated Learning in Mobile Edge Networks: A Comprehensive Survey10.1109/COMST.2020.2986024 ↗
40. Federal snn distillation: A low-communication-cost federated learning framework for spiking neural networks10.1088/1742-6596/2216/1/012078 ↗
41. Yang, S., Linares-Barranco, B., and Chen, B. (2022). Heterogeneous ensemble-based spike-driven few-shot online learning. Front. Neurosci., 16.10.3389/fnins.2022.850932 ↗
42. Automatic seizure detection using multi-resolution dynamic mode decomposition10.1109/ACCESS.2019.2915609 ↗
43. Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection10.1109/TBME.2007.891945 ↗
44. Cui, D., Xia, B., Zhang, R., Sun, Z., Lao, Z., and Wang, W. (2018). A novel intelligent method for the state of charge estimation of lithium-ion batteries using a discrete wavelet transform-based wavelet neural network. Energies, 11.10.3390/en11040995 ↗
45. (2024, June 10). PyTorch. Available online: https://pytorch.org.
46. (2024, June 10). Flask: A Simple Framework for Building Complex Web Applications. Available online: https://palletsprojects.com/p/flask/.
47. Lee, C., Panda, P., Srinivasan, G., and Roy, K. (2018). Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning. Front. Neurosci., 12.10.3389/fnins.2018.00435 ↗
48. (2024, June 10). Spiking Neural Network (SNN) with PyTorch: Towards Bridging the Gap between Deep Learning and the Human Brain. Available online: https://github.com/guillaume-chevalier/Spiking-Neural-Network-SNN-with-PyTorch-where-Backpropagation-engenders-STDP.
49. Backpropagation with biologically plausible spatiotemporal adjustment for training deep spiking neural networks10.1016/j.patter.2022.100522 ↗
50. Hardware implementation of memristor-based artificial neural networks10.1038/s41467-024-45670-9 ↗
51. Kozak, J., Probierz, B., Kania, K., and Juszczuk, P. (2022). Preference-Driven Classification Measure. Entropy, 24.10.3390/e24040531 ↗
52. Lovric, M. (2011). Wilcoxon-Signed-Rank Test. International Encyclopedia of Statistical Science, Springer.10.1007/978-3-642-04898-2 ↗
53. Memristive devices based on mass printed organic resistive switching layers10.1007/s00339-021-04851-9 ↗
54. Three-dimensional memristor circuits as complex neural networks10.1038/s41928-020-0397-9 ↗
55. Noel, M.M., Trivedi, A., and Dutta, P. (2021). Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks. arXiv.
56. Eliasmith, C. (2013). How to Build a Brain: A Neural Architecture for Biological Cognition, Oxford University Press.10.1093/acprof:oso/9780199794546.001.0001 ↗
57. Large-scale synthesis of functional spiking neural circuits10.1109/JPROC.2014.2306061 ↗
58. Conditional routing of information to the cortex: A model of the basal ganglia’s role in cognitive coordination