In-memory hyperdimensional computing

TL;DR

This paper demonstrates an in-memory hyperdimensional computing system using phase-change memory devices that achieves high accuracy in machine learning tasks like language and gesture classification, leveraging in-memory processing for efficiency.

Contribution

It presents a complete in-memory HDC system with a hardware implementation that balances design complexity and accuracy, using nanoscale memristive devices for in-place computation.

Findings

Achieved comparable accuracy to software HDC implementations.

Utilized 760,000 phase-change memory devices for analog in-memory computing.

Validated system on language, news, and gesture recognition tasks.

Abstract

Hyperdimensional computing (HDC) is an emerging computational framework that takes inspiration from attributes of neuronal circuits such as hyperdimensionality, fully distributed holographic representation, and (pseudo)randomness. When employed for machine learning tasks such as learning and classification, HDC involves manipulation and comparison of large patterns within memory. Moreover, a key attribute of HDC is its robustness to the imperfections associated with the computational substrates on which it is implemented. It is therefore particularly amenable to emerging non-von Neumann paradigms such as in-memory computing, where the physical attributes of nanoscale memristive devices are exploited to perform computation in place. Here, we present a complete in-memory HDC system that achieves a near optimum trade-off between design complexity and classification accuracy based on three prototypical HDC related learning tasks, namely, language classification, news classification, and hand gesture recognition from electromyography signals. Comparable accuracies to software implementations are demonstrated, experimentally, using 760,000 phase-change memory devices performing analog in-memory computing.