This Letter presents meaningful results that demonstrate the reduction of dimensionality by spiking neural networks (SNNs) on benchmarking data. This experimental scheme includes metaheuristics, namely, the artificial bee colony algorithm (ABC algorithm) for finding optimal conductance values in the SNNs. Therefore, the objective function in the used ABC algorithm leads the SNNs to compute the principal component analysis (PCA), efficiently. The eigendecomposition of the information drawn by the SNNs in the training phase is the base of the formulated objective function. In these experiments, the Izhikevich model represents the spiking neurons, which have biological plausibility with parameters for reproducing a uniform firing rate. The visualisation of clusters in the 3D PCA space, whose sample values are compared with the PCA function in Matlab, is also shown; this comparison demonstrates an acceptable error in the MSE sense.

References

1. 1)
  - 2. Schliebs, S., Kasabov, N.: ‘Computational modeling with spiking neural networks’, in Kasabov, N. (Ed.): ‘Springer handbook of bio-/neuroinformatics’ (Springer-Verlag, Berlin & Heidelberg, 2014), pp. 625–646.
2. 2)
  - 21. Karaboga, D., Basturk, B.: ‘On the performance of artificial bee colony (ABC) algorithm’, Appl. Soft Comput., 2008, 8, (1), pp. 687–697 (doi: 10.1016/j.asoc.2007.05.007).
3. 3)
  - 1. Izhikevich, E.M.: ‘Dynamical systems in neuroscience: the geometry of excitability and bursting’ (The MIT Press, Cambridge MA, USA, 2007).
4. 4)
  - 3. Sjöström, J., Gerstner, W.: ‘Spike-timing dependent plasticity’, https://icwww.epfl.ch/~gerstner/PUBLICATIONS/STDP-Scholarpedia2010.pdf, accessed September 2018.
5. 5)
  - 10. Center for Machine Learning and Intelligent Systems, University of California, Irvine, USA, http://archive.ics.uci.edu/ml/datasets/Twin+gas+sensor+arrays, accessed January 2019, https://archive.ics.uci.edu/ml/datasets/wine+quality, accessed April 2019, https://archive.ics.uci.edu/ml/datasets/Pen-Based+Recognition+of+Handwritten+Digits, accessed June 2019.
6. 6)
  - 7. Ojha, V.K., Abraham, A., Snasel, V.: ‘Metaheuristic design of feedforward neural networks: a review of two decades of research’, Eng. Appl. Artif. Intell., 2017, 60, pp. 97–116 (doi: 10.1016/j.engappai.2017.01.013).
7. 7)
  - 9. Jolliffe, I.T., Cadima, J.: ‘Principal component analysis: a review and recent developments’, Phil. Trans. R. Soc., 2016, 374, (2064), pp. 1–16, http://dx.doi.org/10.1098/rsta.2015.0202.
8. 8)
  - 5. Vazquez, R.A., Garro, B.A.: ‘Training spiking neural models using artificial bee colony’, Comput. Intell. Neurosci., 2015, 2015, pp. 1–14 (doi: 10.1155/2015/947098).
9. 9)
  - 6. López-Vázquez, G., Ornelas-Rodriguez, M., Espinal, A., et al: ‘Evolutionary spiking neural networks for solving supervised classification problems’, Comput. Intell. Neurosci., 2019, 2019, pp. 1–13 (doi: 10.1155/2019/4182639).
10. 10)
  - 4. Gerstner, W.: ‘Hebbian learning and plasticity’, https://pdfs.semanticscholar.org/f9fc/99a5c52aa5df1b530dfdeb25dfb6b10bdecf.pdf, accessed November 2018.

Spiking neural network approaches PCA with metaheuristics

References

Related content