# Sequence learning, prediction, and replay in networks of spiking neurons

arXiv: https://arxiv.org/abs/2111.03456 · HTML: https://mlsanity.com/paper/2111.03456/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2021.

## Built on by (most cited first, 5 of 5)

- [Threshold Adaptation in Spiking Networks Enables Shortest Path Finding and Place Disambiguation](https://mlsanity.com/paper/2503.21795/) (2025)
- [ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks](https://mlsanity.com/paper/2402.16763/) (2024)
- [Predictive Spike Timing Enables Distributed Shortest Path Computation in Spiking Neural Networks](https://mlsanity.com/paper/2509.10077/) (2025)
- [SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets](https://mlsanity.com/paper/2512.24977/) (2025)
- [Temporal Coding as a Substrate for Sensorimotor Object Inference: A Spiking Reinterpretation of Thousand Brains Architecture](https://mlsanity.com/paper/2605.22206/) (2026)

## Abstract (arXiv)

Sequence learning, prediction and replay have been proposed to constitute the universal computations performed by the neocortex. The Hierarchical Temporal Memory (HTM) algorithm realizes these forms of computation. It learns sequences in an unsupervised and continuous manner using local learning rules, permits a context specific prediction of future sequence elements, and generates mismatch signals in case the predictions are not met. While the HTM algorithm accounts for a number of biological features such as topographic receptive fields, nonlinear dendritic processing, and sparse connectivity, it is based on abstract discrete-time neuron and synapse dynamics, as well as on plasticity mechanisms that can only partly be related to known biological mechanisms. Here, we devise a continuous-time implementation of the temporal-memory (TM) component of the HTM algorithm, which is based on a recurrent network of spiking neurons with biophysically interpretable variables and parameters. The model learns high-order sequences by means of a structural Hebbian synaptic plasticity mechanism supplemented with a rate-based homeostatic control. In combination with nonlinear dendritic input integration and local inhibitory feedback, this type of plasticity leads to the dynamic self-organization of narrow sequence-specific subnetworks. These subnetworks provide the substrate for a faithful propagation of sparse, synchronous activity, and, thereby, for a robust, context specific prediction of future sequence elements as well as for the autonomous replay of previously learned sequences. By strengthening the link to biology, our implementation facilitates the evaluation of the TM hypothesis based on electrophysiological and behavioral data.