.png){kind=icon}
.png){kind=icon}
Return
2T2R RRAM-Based In-Memory Hyperdimensional Computing Encoder for Spatio-Temporal Signal Processing
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSII.2024.3352120.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hyperdimensional computing (HDC) is a brain-inspired computational framework that exploits hypervectors as an alternative to computing with numbers. In-memory computing implementation of HDC (IM-HDC) provides a robust and energy-efficient approach to process spatio-temporal (ST) signals since it significantly reduces data transfer overhead. However, previous IM-HDC suffers from the large peripheral circuit overheads to assist the component-wise hypervector operations. To address these issues, we propose a voltage-mode two-transistor-two-resistor (2T2R) RRAM-based IM-HDC encoder for ST signal processing. The in-memory hyperdimensional encoding has been achieved by performing binding/bundling in the 2T2R RRAM array and permutation on specially designed digital peripheral circuits. Combining with an RRAM-based in-memory associative search module, we validated an average classification accuracy of 97.96% on gesture recognition of electromyogram (EMG) signals, while achieving high robustness and throughput, low latency, and $39\times $ higher energy-efficiency as compared to current state-of-the-art IM-HDC encoders.
Keywords:
Encoding
Quantization (signal)
Energy efficiency
Associative memory
Array signal processing
Robustness
In-memory computing
RRAM
in-memory computing
hyperdimensional computing
spatio-temporal signal
Journal
I
IF:
4.9
Papers:
8.8K
Citations:
2.5W