Abstract
Neuroscience makes use of models of neurons, synapases, and learning rules that modify the efficiency of synapses in stimulating neurons. These models can be used to simulate spiking neural networks, and the standard learning rule is based on the timing of the spikes of the pre and post-synaptic neurons. This paper describes the use of these models to categorise documents by translating this Spike Timing Dependent Plasticity into an unsupervised learning rule by representing documents and categories in neurons and presenting them in specific fashion for learning and categorisation. The resulting system is comparable to other unsupervised machine learning systems. This presentation mechanism is extended to combine input feature value pairs to resolve the exclusive or problem. It is further refined to approximate co-variance of features to an arbitrary degree of precision.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The code can be found on http://www.cwa.mdx.ac.uk/spikeLearn/spikeLearn.html.
- 2.
References
Belavkin, R., Huyck, C.: Conflict resolution and learning probability matching in a neural cell-assembly architecture. Cogn. Syst. Res. 12, 93–101 (2010)
Bi, G., Poo, M.: Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 18(24), 10464–10472 (1998)
Brette, R., Gerstner, W.: Adaptive exponential integrate-and-fire model as an effective description of neuronal activity. J. Neurophysiol. 94, 3637–3642 (2005)
Churchland, P., Sejnowski, T.: The Computational Brain. MIT Press, Cambridge (1999)
Davison, A., Yger, P., Kremkow, J., Perrinet, L., Muller, E.: PyNN: towards a universal neural simulator API in python. BMC Neurosci 8(S2), P2 (2007)
Diehl, P., Cook, M.: Efficient implementation of STDP rules on spinnaker neuromorphic hardware. In: International Joint Conference on Neural Networks (IJCNN), pp. 4288–4295 (2014)
Diehl, P., Cook, M.: Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci 9, 99 (2015)
Furber, S., Galluppi, F., Temple, S., Plana, L.A.: The spinnaker project. Proc. IEEE 102(5), 652–665 (2014). https://doi.org/10.1109/JPROC.2014.2304638
Gewaltig, M., Diesmann, M.: NEST (NEural Simulation Tool). Scholarpedia 2(4), 1430 (2007)
Goldberg, Y., Levy, O.: Word2vec explained: deriving mikolov et al’.s negative-sampling word-embedding method (2014). arXiv arXiv:1402.3722
Hao, Y., Huang, X., Dong, M., Xu, B.: A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule. Neural Netw. 121(8), 387 (2020)
Harnad, S.: The symbol grounding problem. Physica D 42, 335–346 (1990)
Hebb, D.: The Organization of Behavior: A Neuropsychological Theory. Wiley, New York (1949)
Huyck, C.: Learning categories with spiking nets and spike timing dependent plasticity. In: International Conference on Innovative Techniques and Applications of Artificial Intelligence, pp. 139–144 (2020)
Huyck, C.R., Mitchell, I.G.: Post and pre-compensatory Hebbian learning for categorisation. Cogn. Neurodyn. 8(4), 299–311 (2014). https://doi.org/10.1007/s11571-014-9282-4
Kaggle: New article classification using LSTMS (2020). https://www.kaggle.com/atechnohazard/news-article-classification-using-lstms
Kaggle: News article classifier with different models (2020). https://www.kaggle.com/amananandrai/ag-news-classification-dataset?select=train.csv
Kenter, T., Borisov, A., Rijke, M.D.: Siamese cbow: optimizing word embeddings for sentence representationst (2016). arXiv arXiv:1606.04640
Lisman, J.: The challenge of understanding the brain: where we stand in 2015. Neuron 86(4), 864–882 (2015)
McCulloch, W., Pitts, W.: A logical calculus of ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)
Oja, E.: A simplified neuron model as a principal component analyzer. J. Math. Biol. 15, 267–273 (1982)
Rochester, N., Holland, J., Haibt, L., Dudag, W.: Tests on a cell assembly theory of the action of the brain using a large digital computer. Trans. Inf. Theory IT 2, 80–93 (1956)
Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550, 354–59 (2017)
Song, S., Miller, K., Abbott, L.: Competitive hebbian learning through spike-timing-dependent synaptic plasticity. Nat. Neurosci. 3(9), 919–926 (2000)
Thrun, S., et al.: The monk’s problems: a performance comparison of different learning algorithms. Technical Report, CMU-CS-91-197, Carnegie Mellon University, Pittsburgh, PA (1991)
Vigneron, A., Martinet, J.: A critical survey of STDP in spiking neural networks for pattern recognition. In: 2020 International Joint Conference on on Neural Networks (IJCNN), pp. 1–9. IEEE (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huyck, C., Samey, C. (2021). Extended Category Learning with Spiking Nets and Spike Timing Dependent Plasticity. In: Bramer, M., Ellis, R. (eds) Artificial Intelligence XXXVIII. SGAI-AI 2021. Lecture Notes in Computer Science(), vol 13101. Springer, Cham. https://doi.org/10.1007/978-3-030-91100-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-91100-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91099-0
Online ISBN: 978-3-030-91100-3
eBook Packages: Computer ScienceComputer Science (R0)