Abstract: The paper presents a method to classify objects in video streams using a brain-inspired Hierarchical Temporal Memory (HTM) algorithm. Object classification is a challeng-ing task where humans still significantly outperform machine learning algorithms due to their unique capabilities. A system which achieves very promising performance in terms of recogni-tion accuracy have been implemented. Unfortunately, conducting more advanced experiments is very computationally demanding; some of the trials run on a standard CPU may take as long as several days for 960x540 video streams frames. Therefore, authors decided to accelerate selected parts of the system using OpenCL. In particular, authors seek to determine to what extent porting selected and computationally demanding parts of a core may speed up calculations. The classification accuracy of the system was examined through a series of experiments and the performance was given in terms of F1 score as a function of the number of columns, synapses, min overlap and winners set size. The system achieves the highest F1 score of 0.95 and 0.91 for min overlap=4 and 256 synapses, respectively. Authors have also conduced a series of experiments with different hardware setups and measured CPU/GPU acceleration. The best kernel speed-up of 632x and 207x was reached for 256 synapses and 1024 columns. However, overall acceleration including transfer time was significantly lower and amounted to 6.5x and 3.2x for the same setup.

Maciej Wielgosz and Marcin Pietron, “OpenCL-Accelerated Object Classification in Video Streams using Spatial Pooler of Hierarchical Temporal Memory” International Journal of Advanced Computer Science and Applications(IJACSA), 8(2), 2017. http://dx.doi.org/10.14569/IJACSA.2017.080245