# Continuous online sequence learning with an unsupervised neural network model

arXiv: https://arxiv.org/abs/1512.05463 · HTML: https://mlsanity.com/paper/1512.05463/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2015.

## Built on by (most cited first, 18 of 18)

- [Continual Learning for Recurrent Neural Networks: an Empirical Evaluation](https://mlsanity.com/paper/2103.07492/) (2021)
- [Deep Learning for Anomaly Detection in Log Data: A Survey](https://mlsanity.com/paper/2207.03820/) (2022)
- [BayesPCN: A Continually Learnable Predictive Coding Associative Memory](https://mlsanity.com/paper/2205.09930/) (2022)
- [Fast Online Changepoint Detection via Functional Pruning CUSUM statistics](https://mlsanity.com/paper/2110.08205/) (2021)
- [Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computing](https://mlsanity.com/paper/2206.13336/) (2022)
- [Sustainable Artificial Intelligence through Continual Learning](https://mlsanity.com/paper/2111.09437/) (2021)
- [Computation with Sequences in a Model of the Brain](https://mlsanity.com/paper/2306.03812/) (2023)
- [Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning](https://mlsanity.com/paper/2503.21419/) (2025)
- [Scope and Sense of Explainability for AI-Systems](https://mlsanity.com/paper/2112.10551/) (2021)
- [Neuronal Auditory Machine Intelligence (NEURO-AMI) In Perspective](https://mlsanity.com/paper/2401.02421/) (2023)
- [Distal Interference: Exploring the Limits of Model-Based Continual Learning](https://mlsanity.com/paper/2402.08255/) (2024)
- [Cloud Failure Prediction with Hierarchical Temporal Memory: An Empirical Assessment](https://mlsanity.com/paper/2110.03431/) (2021)
- [A Hierarchical Approach to Conditional Random Fields for System Anomaly Detection](https://mlsanity.com/paper/2210.15030/) (2022)
- [A Brain-Inspired Sequence Learning Model based on a Logic](https://mlsanity.com/paper/2308.12486/) (2023)
- [Spatially-resolved hyperlocal weather prediction and anomaly detection using IoT sensor networks and machine learning techniques](https://mlsanity.com/paper/2310.11001/) (2023)
- [Architecture of a Cortex Inspired Hierarchical Event Recaller](https://mlsanity.com/paper/2405.02371/) (2024)
- [SNN-Based Online Learning of Concepts and Action Laws in an Open World](https://mlsanity.com/paper/2411.12308/) (2024)
- [Enhancing Biologically Inspired Hierarchical Temporal Memory with Hardware-Accelerated Reflex Memory](https://mlsanity.com/paper/2504.03746/) (2025)

## Abstract (arXiv)

The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory is recently proposed as a theoretical framework for sequence learning in the cortex. In this paper, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data. We show the model is able to continuously learn a large number of variable-order temporal sequences using an unsupervised Hebbian-like learning rule. The sparse temporal codes formed by the model can robustly handle branching temporal sequences by maintaining multiple predictions until there is sufficient disambiguating evidence. We compare the HTM sequence memory with other sequence learning algorithms, including statistical methods: autoregressive integrated moving average (ARIMA), feedforward neural networks: online sequential extreme learning machine (ELM), and recurrent neural networks: long short-term memory (LSTM) and echo-state networks (ESN), on sequence prediction problems with both artificial and real-world data. The HTM model achieves comparable accuracy to other state-of-the-art algorithms. The model also exhibits properties that are critical for sequence learning, including continuous online learning, the ability to handle multiple predictions and branching sequences with high order statistics, robustness to sensor noise and fault tolerance, and good performance without task-specific hyper- parameters tuning. Therefore the HTM sequence memory not only advances our understanding of how the brain may solve the sequence learning problem, but is also applicable to a wide range of real-world problems such as discrete and continuous sequence prediction, anomaly detection, and sequence classification.