Spike Timing Dependent Plasticity Versus Intrinsic Plasticity as Feature Extraction Technique

Petia Koprinkova-Hristova

doi:10.2478/cait-2026-0010

Abstract

This work investigates the effect of Spike Timing-Dependent Plasticity (STDP) of the synapses in the randomly connected Spiking Neural Networks (SNN) on the distribution of the firing rates of the individual neurons. It was observed that STDP, as a homeostatic plasticity rule, forces SNN activity to reflect the input structure. This effect is similar but not identical to the Intrinsic Plasticity (IP) tuning of Reservoir Computing (RC) recurrent neural networks. Both IP and STDP rules allow for capturing of the input data structure into the network state. This explains why STDP-trained SNNs are good for feature extraction from multidimensional data for classification purposes.

References

Andrews, D. F. Plots of High-Dimensional Data. – Biometrics, Vol. 28, 1972, No 1, pp. 125-136.
Search in Google Scholar Back to article
Basalyga, G., P. M. Gleiser, T. Wennekers. Emergence of Small-World Structure in Networks of Spiking Neurons through STDP Plasticity. – Adv. Exp. Med. Biol., Vol. 718, 2011, pp. 33-9.
Search in Google Scholar Back to article
Belatreche, B., R. Paul. Dynamic Cluster Formation Using Populations of Spiking Neurons. – In: Proc. of IEEE World Congress on Computational Intelligence “WCCI’12”, Brisbane, Australia, 10-15 June 2012.
Search in Google Scholar Back to article
Cateau, H., K. Kitano, T. Fukai. Interplay between a Phase Response Curve and Spike-Timing-Dependent Plasticity Leading to Wireless Clustering. – Phys. Rev. E, Vol. 77, 2008, No 5, 051909.
Search in Google Scholar Back to article
Chaudhari, S., H. Nair, J. M. F. Moura, J. PaulShen. Unsupervised Clustering of Time Series Signals Using Neuromorphic Energy-Efficient Temporal Neural Networks. – In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’21), Toronto, ON, Canada, 2021, pp. 7873-7877.
Search in Google Scholar Back to article
Debanne, D., Y. Inglebert. Spike Timing-Dependent Plasticity and Memory. – Current Opinion in Neurobiology, Vol. 80, 2023, 102707.
Search in Google Scholar Back to article
Gewaltig, M.-O., M. Diesmann. NEST (Neural Simulation Tool). – Scholarpedia, Vol. 2, 2007, No 4, 1430.
Search in Google Scholar Back to article
Guetig, R., R. Aharonov, S. Rotter, H. Sompolinsky. Learning Input Correlations through Nonlinear Temporally Asymmetric Hebbian Plasticity. – Journal of Neuroscience, Vol. 23, 2003, pp. 3697-3714.
Search in Google Scholar Back to article
Huo, B., F. Li, S. Peng, H. Chen, S. Xin, H. Wang. Research on SNN Learning Algorithms and Networks Based on Biological Plausibility. – IEEE Access, Vol. 13, 2025, pp. 95243-95256.
Search in Google Scholar Back to article
Izhikevich, E. M. Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting. The MIT Press, 2007.
Search in Google Scholar Back to article
Jaeger, H. Tutorial on Training Recurrent Neural Networks, Covering BPPT, RTRL, EKF, and the “Echo State Network” Approach. GMD Report 159, German National Research Center for Information Technology, 2002.
Search in Google Scholar Back to article
Kasabov, N. Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence. Springer Series on Bio- and Neurosystems, 2019.
Search in Google Scholar Back to article
Khalid, T. K., S. Nasreen. A Survey of Feature Selection and Feature Extraction Techniques in Machine Learning. – In: Proc. of Science and Information Conference, London, UK, 2014, pp. 372-378.
Search in Google Scholar Back to article
Koprinkova-Hristova, P. Multi-Dimensional Data Clustering and Visualization via Echo State Networks. – In: R. Kountchev, K. Nakamatsu, Eds. New Approaches in Intelligent Image Analysis. Intelligent Systems Reference Library. Vol. 108. Cham, Springer, 2016.
Search in Google Scholar Back to article
Koprinkova-Hristova, P., I. Georgiev, M. Raykovska. Echo State Network for Features Extraction and Segmentation of Tomography Images. – Computer Science and Information Systems, Vol. 21, 2024, No 1, pp. 379-393.
Search in Google Scholar Back to article
Koprinkova-Hristova, P., D. Penkov, S. Nedelcheva, S. Yordanov, N. Kasabov. On-Line Learning, Classification and Interpretation of Brain Signals Using 3D SNN and ESN. – In: Proc. of International Joint Conference on Neural Networks (IJCNN’23), Gold Coast, Australia, 2023, pp. 1-6.
Search in Google Scholar Back to article
Koprinkova-Hristova, P., M. Stefanova, B. Genova, N. Bocheva. Echo State Network for Classification of Human Eye Movements during Decision Making. – In: L. Iliadis, I. Maglogiannis, V. Plagianakos, Eds. Artificial Intelligence Applications and Innovations (AIAI’18). IFIP Advances in Information and Communication Technology. Vol. 519. Cham, Springer, 2018.
Search in Google Scholar Back to article
Li, X., M. Small. Enhancement of Signal Sensitivity in a Heterogeneous Neural Network Refined from Synaptic Plasticity. – New J. Phys., Vol. 12, 2010, 083045.
Search in Google Scholar Back to article
Majumdar, P. Spiking Neural Networks: A Comprehensive Review of Diverse Applications, Research Progress, Challenges, and Future Research Directions. – Evolving Systems, Vol. 16, 2025, 125.
Search in Google Scholar Back to article
Masquelier, T., R. Guyonneau, S. J. Thorpe. Spike Timing Dependent Plasticity Finds the Start of Repeating Patterns in Continuous Spike Trains. – PLoS ONE, Vol. 3, 2008, No 1, e1377.
Search in Google Scholar Back to article
Masquelier, T., S. J. Thorpe. Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity. – PLoS Comput Biol., Vol. 3, 2007, No 2, e31.
Search in Google Scholar Back to article
Mutlag, W. K., S. K. Ali, Z. M. Aydam, B. H. Taher. Feature Extraction Methods: A Review. – J. Phys.: Conf. Ser., Vol. 1591, 2020, 012028.
Search in Google Scholar Back to article
Rohr, V., R. Berner, E. L. Lameu, O. V. Popovych, S. Yanchuk. Frequency Cluster Formation and Slow Oscillations in Neural Populations with Plasticity. – PLoS ONE, Vol. 14, 2019, No 11, e0225094.
Search in Google Scholar Back to article
Rotter, S., M. Diesmann. Exact Digital Simulation of Time-Invariant Linear Systems with Applications to Neuronal Modeling. – Biol. Cybern., Vol. 81, 1999, pp. 381-402.
Search in Google Scholar Back to article
Safa, A. Continual Learning with Hebbian Plasticity in Sparse and Predictive Coding Networks: A Survey and Perspective. – Neuromorph. Comput. Eng., Vol. 4, 2024, 042001.
Search in Google Scholar Back to article
Schrauwen, B., M. Wandermann, D. Verstraeten, J. J. Steil, D. Stroobandt. Improving Reservoirs Using Intrinsic Plasticity. – Neurocomputing, Vol. 71, 2008, pp. 1159-1171.
Search in Google Scholar Back to article
Tal, A., N. Peled, H. T. Siegelmann. Biologically Inspired Load Balancing Mechanism in Neocortical Competitive Learning. – Frontiers in Neural Circuits, Vol. 8, 2014, 18.
Search in Google Scholar Back to article

Spike Timing Dependent Plasticity Versus Intrinsic Plasticity as Feature Extraction Technique

Abstract

Paradigm

My account