In-memory hyperdimensional computing
This work addresses the problem of computational efficiency for machine learning practitioners by enabling robust HDC on non-von Neumann hardware, though it is incremental as it applies an existing method to new hardware.
The authors tackled the challenge of implementing hyperdimensional computing (HDC) efficiently by developing an in-memory computing system using phase-change memory devices, achieving comparable accuracies to software implementations on tasks like language classification and hand gesture recognition with 760,000 devices.
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.