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.
Structural plasticity is required by HTM models, but not addressed in many hardware architectures. This paper presents a model of topographic map formation that is implemented on the SpiNNaker neuromorphic platform, running in real time using point neurons, and making use of both synaptic rewiring and spike-timing dependent plasticity (STDP). The authors use our papers as one of the motivations for working on this architecture.
This paper proposes an anomaly detection framework for scientific workflows that is based on our Hierarchical Temporal Memory (HTM) technology. The paper also cites the Numenta Anomaly Benchmark (NAB) scoring code and methodology; the researchers use NAB to evaluate performance of algorithms.
The authors proposes a distributed anomaly detection system using hierarchical temporal memory (HTM) that predicts the flow of data in real time to increase security for a vehicular controller area network bus. The HTM-based anomaly detection system achieved better results than systems based on recurrent neural networks and hidden Markov model detection.
