Continuous online sequence learning with an unsupervised neural network model

DOI10.1162/NECO_A_00893zbMATH Open1474.68249arXiv1512.05463OpenAlexW2964284952WikidataQ39391752 ScholiaQ39391752MaRDI QIDQ5380592FDOQ5380592

Authors: Yuwei Cui, Subutai Ahmad, Jeff Hawkins 

Publication date: 5 June 2019

Published in: Neural Computation (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1512.05463

Recommendations

• Learning a sparse code for temporal sequences using STDP and sequence compression
• Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning
• Sequence memory based on an oscillatory neural network
• On-line learning on temporal manifolds
• Implicit sequence learning in recurrent neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Neural biology (92C20) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Title not available (Why is that?)
• Pattern recognition and machine learning.
• Knowledge discovery from data streams.
• Time series analysis by state space methods.
• Title not available (Why is that?)
• On-board mining of data streams in sensor networks
• Empirical evaluation of the improved rprop learning algorithms
• The hierarchical hidden Markov model: Analysis and applications
• Title not available (Why is that?)
• Learning in non-stationary environments. Methods and applications
• Supervised sequence labelling with recurrent neural networks.
• Title not available (Why is that?)
• Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting
• Investigating the Fault Tolerance of Neural Networks

Cited In (2)

• On-line learning on temporal manifolds
• Nearest neighbor forecasting using sparse data representation

Uses Software

• forecast
• Forecast
• PyBrain
• word2vec
• fpp
• PRMLT

This page was built for publication: Continuous online sequence learning with an unsupervised neural network model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380592)