Abstract
Artificial neural networks based on sigmoidal neurons have achieved undisputed performance in various tasks, including image recognition and classification. The search for more biologically plausible artificial neuron models led to the creation of pulsed models. The new way of encoding information is through discrete pulses, and the timing of these pulses is important for the result. This work proposes the creation of a neural network with pulsed neurons for the task of image classification. The network uses cell models more similar to those found in animal brains, communicating through spikes and relying on a stochastic component for pulse generation. It also applies STDP as an unsupervised learning rule, very similar to human learning. Experiments were run using various parameter sets to study the network's dynamics in the image classification task. The results obtained were analyzed, and their performance indicates a promising method capable of good performance on three known image databases (Caltech 101, ETH-80, and MNIST). The database 1 achieved a classification accuracy of 87%, database 2 achieved 77% on ETH-80, and database 3 achieved 86% on MNIST respectively.
References
Li, C., Ma, L., and Furber, S. "Quantization framework for fast spiking neural networks." Frontiers in Neuroscience 16 (2022): 918793.
Fang, W., Yu, Z., Chen, Y., Masquelier, T., Huang, T., and Tian, Y. "Incorporating learnable membrane time constant to enhance learning of spiking neural networks." Proceedings of the AAAI Conference on Artificial Intelligence (2020): 2661–2671.
Taherkhani, A., Belatreche, A., Li, Y., Cosma, G., Maguire, L.P., and McGinnity, T.M. "A review of learning in biologically plausible spiking neural networks." Neural Networks 122 (2020): 253–272.
Davidson, S., and Furber, S.B. "Comparison of artificial and spiking neural networks on digital hardware." Frontiers in Neuroscience 15 (2021): 4523.
Han, J., Choi, J., and Lee, C. "Image denoising method based on deep learning using improved U-net." IEIE Transactions on Smart Processing and Computing 10, no. 4 (2021): 291–295.
Rashed-Al-Mahfuz, M., Moni, M.A., Lio, P., Islam, S.M.S., Berkovsky, S., and Khushi, M. "Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions." Biomedical Engineering Letters 11, no. 2 (2021): 147–162.
Young, S., Wang, Z., Taubman, D., and Girod, B. "Transform quantization for CNN compression." IEEE Transactions on Pattern Analysis and Machine Intelligence (2021): 1.
Kim, S., Park, S., Na, B., and Yoon, S. "Spiking-YOLO: spiking neural network for energy-efficient object detection." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 7 (2020): 11270–11277.
Parvizi-Fard, A., Amiri, M., Kumar, D., Iskarous, M.M., and Thakor, N.V. "A functional spiking neuronal network for tactile sensing pathway to process edge orientation." Scientific Reports 11 (2021): 1320.
Auge, D., Hille, J., Mueller, E., and Knoll, A. "A survey of encoding techniques for signal processing in spiking neural networks." Neural Processing Letters 53, no. 5 (2021): 4693–4710.
Kag, A., and Saligrama, V. "Training recurrent neural networks via forward propagation through time." Proceedings of the 38th International Conference on Machine Learning (PMLR) (2021): 5189–5200.
Zhong, Y., and Huang, X. "A painting style system using an improved CNN algorithm." IEIE Transactions on Smart Processing and Computing 11, no. 4 (2022): 332–342.
Wang, S., Cheng, T.H., and Lim, M.-H. "LTMD: learning improvement of spiking neural networks with learnable thresholding neurons and moderate dropout." Advances in Neural Information Processing Systems 35 (2022): 28350–28362.
Valencia, D., and Alimohammad, A. "Towards in vivo neural decoding." Biomedical Engineering Letters 12, no. 2 (2022): 185–195.
Nao, S., and Wang, Y. "Speckle noise removal model based on diffusion equation and convolutional neural network." Computational Intelligence and Neuroscience (2022): 5344263.
Kheradpisheh, S.R., Ganjtabesh, M., Thorpe, S.J., and Masquelier, T. "STDP-based spiking deep convolutional neural networks for object recognition." Neural Networks 99 (2018): 56–67.
Li, Y., Deng, S., Dong, X., Gong, R., and Gu, S. "A free lunch from ANN: towards efficient, accurate spiking neural networks calibration." Proceedings of the 38th International Conference on Machine Learning (PMLR) (2021): 6316–6325.
Makarov, V.A., Lobov, S.A., Shchanikov, S., Mikhaylov, A., and Kazantsev, V.B. "Toward reflective spiking neural networks exploiting memristive devices." Frontiers in Computational Neuroscience 16 (2022): 859874.
Juarez-Lora, A., Ponce-Ponce, V.H., Sossa, H., and Rubio-Espino, E. "R-STDP spiking neural network architecture for motion control on a changing friction joint robotic arm." Frontiers in Neurorobotics 16 (2022): 904017.
Yamazaki, K., Vo-Ho, V.-K., Bulsara, D., and Le, N. "Spiking neural networks and their applications: A review." Brain Sciences 12, no. 7 (2022): 863.
Naderi, R., Rezaei, A., Amiri, M., et al. "Unsupervised post-training learning in spiking neural networks." Scientific Reports 15 (2025): 17647.
Yang, G., Lee, W., Seo, Y., Lee, C., Seok, W., Park, J., Sim, D., and Park, C. "Unsupervised spiking neural network with dynamic learning of inhibitory neurons." Sensors 23, no. 16 (2023): 7232.
Szczęsny, S., Huderek, D., and Przyborowski, Ł. "Explainable spiking neural network for real time feature classification." Journal of Experimental and Theoretical Artificial Intelligence 35, no. 1 (2023): 77–92.
Pietrzak, P., Szczęsny, S., Huderek, D., and Przyborowski, Ł. "Overview of spiking neural network learning approaches and their computational complexities." Sensors 23, no. 6 (2023): 3037.
Niu, L.-Y., Wei, Y., Liu, W.-B., Long, J.-Y., and Xue, T.-H. "Research progress of spiking neural network in image classification: A review." Applied Intelligence 53, no. 16 (2023): 19466–19490.