RT Journal Article
A1 Aidana Irmanova
A1 Timur Ibrayev
A1 Alex Pappachen James

PB iet
T1 Discrete-level memristive circuits for HTM-based spatiotemporal data classification system
JN IET Cyber-Physical Systems: Theory & Applications
VO 3
IS 1
SP 34
OP 43
AB The authors propose a discrete-level memristive memory design for analogue data processing in hardware implementations of hierarchical temporal memory (HTM). In this study, memristors were set to ternary and quaternary states in a sub-cell by application of different write voltage levels through a resistive network configuration. Simulations of the proposed circuit show that the highest number of discrete output levels of the memory was achieved using quaternary logic. However overall, using the same number of sub-cells and ternary logic exhibits the lowest relative error rate. For data classification purposes, the proposed discrete-level memristive cells are incorporated into the TM of HTM architecture, and its hardware circuit is presented for pattern recognition. They report improved results of face recognition using AR, ORL and UFI databases, and TIMIT database for speech recognition. These results are compared with the earlier design of HTM having only the spatial pooler (SP). Accuracy of the HTM architecture incorporating both SP and TM with discrete-level memristive cells for face recognition increased from 76.5 to 83.5% for AR database and speech recognition accuracy is improved from 73.3 to 93.3%.
K1 write voltage levels
K1 quaternary states
K1 analogue data processing
K1 HTM architecture
K1 hardware circuit
K1 pattern recognition
K1 discrete-level memristive cells
K1 hardware implementations
K1 quaternary logic
K1 hierarchical temporal memory
K1 resistive network configuration
K1 discrete-level memristive memory design
K1 face recognition
K1 discrete-level memristive circuits
K1 HTM-based spatiotemporal data classification system
K1 spatial pooler
K1 speech recognition
DO https://doi.org/10.1049/iet-cps.2017.0053
UL https://digital-library.theiet.org/;jsessionid=38scae8akbpmp.x-iet-live-01content/journals/10.1049/iet-cps.2017.0053
LA English
SN
YR 2018
OL EN