Exploration of 2-neuron memory units in spiking neural networks

 pdf (7865K)

Working memory mechanisms in spiking neural networks consisting of leaky integrate-and-fire neurons with adaptive threshold and synaptic plasticity are studied in this work. Moderate size networks including thousands of neurons were explored. Working memory is a network ability to keep in its state the information about recent stimuli presented to the network such that this information is sufficient to determine which stimulus has been presented. In this study, network state is defined as the current characteristics of network activity only — without internal state of its neurons. In order to discover the neuronal structures serving as a possible substrate of the memory mechanism, optimization of the network parameters and structure using genetic algorithm was carried out. Two kinds of neuronal structures with the desired properties were found. These are neuron pairs mutually connected by strong synaptic links and long tree-like neuronal ensembles. It was shown that only the neuron pairs are suitable for efficient and reliable implementation of working memory. Properties of such memory units and structures formed by them are explored in the present study. It is shown that characteristics of the studied two-neuron memory units can be set easily by the respective choice of the parameters of its neurons and synaptic connections. Besides that, this work demonstrates that ensembles of these structures can provide the network with capability of unsupervised learning to recognize patterns in the input signal.

Keywords: spiking neural network, homeostatic synaptic plasticity, spatio-temporal pattern recognition, working memory, LIF neuron with adaptive threshold, STDP
Citation in English: Kiselev M.V. Exploration of 2-neuron memory units in spiking neural networks // Computer Research and Modeling, 2020, vol. 12, no. 2, pp. 401-416
Citation in English: Kiselev M.V. Exploration of 2-neuron memory units in spiking neural networks // Computer Research and Modeling, 2020, vol. 12, no. 2, pp. 401-416
DOI: 10.20537/2076-7633-2020-12-2-401-416

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the List of Russian peer-reviewed journals publishing the main research results of PhD and doctoral dissertations.

International Interdisciplinary Conference "Mathematics. Computing. Education"

The journal is included in the RSCI

Indexed in Scopus