Hyperdimensional Computing (HDC) is a brain-inspired and light-weight machine learning method. It has received significant attention in the literature as a candidate to be applied in the wearable internet of things, near-sensor artificial intelligence applications and on-device processing. HDC is computationally less complex than traditional deep learning algorithms and typically achieves moderate to good classification performance. A key aspect that determines the performance of HDC is the encoding of the input data to the hyperdimensional (HD) space. This article proposes a novel light-weight approach relying only on native HD arithmetic vector operations to encode binarized images that preserves similarity of patterns at nearby locations by using point of interest selection and local linear mapping. The method reaches an accuracy of 97.35% on the test set for the MNIST data set and 84.12% for the Fashion-MNIST data set. These results outperform other studies using baseline HDC with different encoding approaches and are on par with more complex hybrid HDC models. The proposed encoding approach also demonstrates a higher robustness to noise and blur compared to the baseline encoding.

翻译：超维计算（HDC）是一种受大脑启发的轻量级机器学习方法。作为可应用于可穿戴物联网、近传感器人工智能应用及设备端处理的候选技术，该方法在文献中受到广泛关注。与传统深度学习算法相比，HDC具有更低的计算复杂度，通常能实现中等至良好的分类性能。决定HDC性能的关键因素在于输入数据向超维空间的编码方式。本文提出一种新型轻量级方法，仅依赖原生超维算术向量运算对二值化图像进行编码，通过兴趣点选取与局部线性映射保留邻近位置模式的相似性。该方法在MNIST数据集测试集上达到97.35%的准确率，在Fashion-MNIST数据集上达到84.12%的准确率。这些结果优于采用不同编码方法的基线HDC研究，并与更复杂的混合HDC模型性能相当。与基线编码方法相比，所提出的编码方法还展现出更强的噪声与模糊鲁棒性。