In this paper, we investigate and evaluate the use of hierarchical temporal memory (HTM) for short-term prediction of traffic flows over real-world Sydney Coordinated Adaptive Traffic System data on arterial roads in the Adelaide metropolitan area in South Australia. Results are compared with those from long-short-term memory (LSTM). Extended experimentation with LSTM network configurations in both batch learning and online learning modes provide results with superior predictive performance over previous usage of LSTM and other deep learning techniques for short-term traffic flow prediction. In addition, we argue that HTM has potential as an effective tool for short term traffic flow prediction with results on par with LSTM and improvements when traffic flow distributions change.
This paper presents a new model of an associative memory that overcomes the typical deficiencies of spurious memories and low efficiency. The authors refer to it as associative memory (SAM) because it is based on sparse projections from neural patterns to pattern-specific neurons. This paper was inspired by the paper, ‘Why neurons have thousands of synapses, a theory of sequence memory in neocortex.’
In this Master Thesis from KTH Royal Institute of Technology, the author developed a machine learning model with Numenta’s HTM technology with the goal to solve the task of detecting and classifying anomalies in system logs belonging to Ericsson’s component based architecture applications. The results are then compared to an existing classifier, called Linnaeus, which uses classical machine learning methods. The HTM model is able to show promising capabilities of classifying system log sequences with similar results compared with the Linnaeus model.
In this Master’s thesis from the University of Agder, the authors examine using Hierarchical Temporal Memory (HTM) to predict future purchase events of customers in a non-contractual setting. HTM was chosen specifically because of a desire to research algorithms that may be useful in churn analysis by utilizing temporal structure of data in prediction based models. The authors also compare HTM results to other techniques.
The authors present a full-scale Hierarchical Temporal Memory (HTM) architecture for spatial pooler and temporal memory and verify it for two data sets: MNIST and the European number plate font (EUNF), with and without noise. These results suggest that the proposed architecture, using a novel form of synthetic synapses, can serve as a digital core to build HTM in hardware.