Continuous online sequence learning with an unsupervised neural network model

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.

Preprint of journal submission

References in corpus (8)

• Deep Learning in Neural Networks: An Overview
• Improving neural networks by preventing co-adaptation of feature detectors
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark
• Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
• Properties of Sparse Distributed Representations and their Application to Hierarchical Temporal Memory
• How do neurons operate on sparse distributed representations? A mathematical theory of sparsity, neurons and active dendrites
• Encoding Data for HTM Systems

Cited by in corpus (17)

• Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
• Deep Learning for Anomaly Detection in Log Data: A Survey
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Real-Time Anomaly Detection for Streaming Analytics
• A Review of 40 Years of Cognitive Architecture Research: Core Cognitive Abilities and Practical Applications
• Sequence learning, prediction, and replay in networks of spiking neurons
• Harnessing adaptive dynamics in neuro-memristive nanowire networks for transfer learning
• Using Spatial Pooler of Hierarchical Temporal Memory to classify noisy videos with predefined complexity
• Non-volatile Hierarchical Temporal Memory: Hardware for Spatial Pooling
• Hybrid Forest: A Concept Drift Aware Data Stream Mining Algorithm
• Local Unsupervised Learning for Image Analysis
• Multi-timescale memory dynamics in a reinforcement learning network with attention-gated memory
• CLAASIC: a Cortex-Inspired Hardware Accelerator
• p-DLA: A Predictive System Model for Onshore Oil and Gas Pipeline Dataset Classification and Monitoring - Part 1
• Hardware based Spatio-Temporal Neural Processing Backend for Imaging Sensors: Towards a Smart Camera
• Problem-Adapted Artificial Intelligence for Online Network Optimization
• Deviant Learning Algorithm: Learning Sparse Mismatch Representations through Time and Space