QubitHD: A Stochastic Acceleration Method for HD Computing-Based Machine Learning
This work addresses energy efficiency challenges in machine learning for resource-constrained applications, offering a novel method to enhance performance without sacrificing accuracy.
The paper tackles the trade-off between energy efficiency and classification accuracy in brain-inspired hyperdimensional computing by proposing QubitHD, a stochastic binarization method that maintains comparable accuracy while improving energy efficiency by 65% and training time by 95% compared to state-of-the-art HD-based algorithms.
Machine Learning algorithms based on Brain-inspired Hyperdimensional(HD) computing imitate cognition by exploiting statistical properties of high-dimensional vector spaces. It is a promising solution for achieving high energy efficiency in different machine learning tasks, such as classification, semi-supervised learning, and clustering. A weakness of existing HD computing-based ML algorithms is the fact that they have to be binarized to achieve very high energy efficiency. At the same time, binarized models reach lower classification accuracies. To solve the problem of the trade-off between energy efficiency and classification accuracy, we propose the QubitHD algorithm. It stochastically binarizes HD-based algorithms, while maintaining comparable classification accuracies to their non-binarized counterparts. The FPGA implementation of QubitHD provides a 65% improvement in terms of energy efficiency, and a 95% improvement in terms of training time, as compared to state-of-the-art HD-based ML algorithms. It also outperforms state-of-the-art low-cost classifiers (such as Binarized Neural Networks) in terms of speed and energy efficiency by an order of magnitude during training and inference.