Continuous online sequence learning with an unsupervised neural network model

TL;DR

This paper demonstrates that hierarchical temporal memory (HTM) can continuously learn and predict complex temporal sequences in an unsupervised manner, showing robustness and versatility comparable to state-of-the-art algorithms.

Contribution

It provides a detailed analysis of HTM sequence memory properties and applies it to real-world sequence learning and prediction tasks, highlighting its robustness and online learning capabilities.

Findings

HTM can learn many variable-order sequences continuously and unsupervised.

The model handles branching sequences with multiple predictions and disambiguation.

HTM achieves accuracy comparable to other advanced sequence learning algorithms.

Abstract

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.