Learning compositional sequences with multiple time scales through a hierarchical network of spiking neurons

Abstract

Sequential behaviour is often compositional and organised across multiple time scales: a set of individual elements developing on short time scales (motifs) are combined to form longer functional sequences (syntax). Such organisation leads to a natural hierarchy that can be used advantageously for learning, since the motifs and the syntax can be acquired independently. Despite mounting experimental evidence for hierarchical structures in neuroscience, models for temporal learning based on neuronal networks have mostly focused on serial methods. Here, we introduce a network model of spiking neurons with a hierarchical organisation aimed at sequence learning on multiple time scales. Using biophysically motivated neuron dynamics and local plasticity rules, the model can learn motifs and syntax independently. Furthermore, the model can relearn sequences efficiently and store multiple sequences. Compared to serial learning, the hierarchical model displays faster learning, more flexible relearning, increased capacity, and higher robustness to perturbations. The hierarchical model redistributes the variability: it achieves high motif fidelity at the cost of higher variability in the between-motif timings.

Long- and short-term history effects in a spiking network model of statistical learning

“…The plastic weights learn the correct transformation, in this case, the inverse of the cumulative distribution function F −1 ( u ). This is related to previous work on learning and generating sequences (Nicola and Clopath 2017; Maes et al 2020; Maes et al 2021). In this previous work, the backbone consists not of randomly switching clusters but clusters active sequentially in a chain.…”

“…The plastic weights learn the correct transformation, in this case, the inverse of the cumulative distribution function −1 ( ). This is related to previous work on learning and generating sequences (Nicola and Clopath 2017;Maes et al 2020;Maes et al 2021).…”

“…The parameters of the neurons do not change depending on which network they belong to. Parameters are taken from Brette and Gerstner 2005; Clopath et al 2010; Litwin-Kumar and Doiron 2014; Maes et al 2020; Maes et al 2021.…”

“…Parameters were not fine tuned. They are set to match similar activities across the different networks, and are taken from Litwin-Kumar and Doiron 2014; Maes et al 2020; Maes et al 2021.…”

“…Neuronal membrane dynamics parameters. Parameters taken fromBrette and Gerstner 2005;Clopath et al 2010;Litwin-Kumar and Doiron 2014;Maes et al 2020;Maes et al 2021. …”