This paper devises a continuous-time implementation of the temporal-memory component of HTM, which is based on a recurrent network of spiking neurons with biophysically interpretable variables and parameters. It demonstrates this aspect by studying the effect of the sequence speed on the sequence learning performance and on the speed of autonomous sequence replay.
Drawing inspirations from the Thousand Brains Theory on Intelligence, this paper from Ghent University proposes an active inference agent that actively gathers evidence for object classifications, and can learn novel object categories over time. The researchers show that the agent is able to learning object identity and pose representations from pixel observations.
The sparse distributed representation is the basis of the HTM model, but the existing spatial pool learning algorithms have high training time overhead and may cause the spatial pool to become unstable. In this paper from Jiangsu University, researchers propose a fast spatial pool learning algorithm of HTM based on minicolumn’s nomination, where the minicolumns are selected according to the load-carrying capacity and the synapses are adjusted using compressed encoding, to overcome these disadvantages.
In this doctoral dissertation from Nova Southeastern University, the author developed an HTM sequence classifier aimed at classifying streaming data, which contained concept drift, noise, and temporal dependencies. The HTM sequence classifier was fed both artificial and real-world data streams and evaluated using the prequential evaluation method. Furthermore, this research explored the suitability of the HTM sequence classifier for detecting stalling code within evasive malware. It highlights the potential of HTM technology for application in online classification problems and the detection of evasive malware.
Neuromorphic systems that learn and predict from streaming inputs hold significant promise in pervasive edge computing and its applications. In this paper, a neuromorphic system that processes spatio-temporal information on the edge is proposed. Algorithmically, the system is based on HTM, or hierarchical temporal memory, that inherently offers online learning, resiliency, and fault tolerance. Architecturally, it is a full custom mixed-signal design with an underlying digital communication scheme and analog computational modules. Therefore, the proposed system features reconfigurability, real-time processing, low power consumption, and low-latency processing.