QuantHD: A Quantization Framework for Hyperdimensional Computing
QuantHD: A Quantization Framework for Hyperdimensional Computing
复制标题
DOI：
10.1109/tcad.2019.2954472
复制
发表时间：
2020-10-01
影响因子：
2.9
通讯作者：
Rosing, Tajana
中科院分区：
文献类型：
--
作者：
Imani, Mohsen;Bosch, Samuel;Rosing, Tajana
大脑启发的超维（HD）计算模型的认知，利用高维矩阵的属性-高维向量，而不是与现代处理器中使用的数值。现有的HD计算算法的一个根本弱点是，它们需要使用浮点模型，以提供可接受的准确度对现实的分类问题。然而，使用浮点值会显著增加HD计算成本。为了解决这个问题，我们提出了QuantHD，这是一种在训练过程中量化HD计算模型的新框架。QuantHD使HD计算能够与低成本量化模型（二进制或三进制模型）一起工作，同时提供与浮点模型相似的精度。因此，我们提出了一个FPGA实现，加速HD计算在训练和推理阶段。我们评估QuantHD的准确性和效率在各种现实世界的应用，并观察到QuantHD可以实现平均17.2%的准确性提高相比，现有的二进制HD计算算法，提供了类似的计算成本。在效率方面，与最先进的HD计算算法相比，QuantHD FPGA实现可以在推理（训练）期间实现平均42.3倍和4.7倍（34.1倍和4.1倍）的能效改进和加速。
Brain-inspired hyperdimensional (HD) computing models cognition by exploiting properties of high dimensional statistics-high-dimensional vectors, instead of working with numeric values used in contemporary processors. A fundamental weakness of existing HD computing algorithms is that they require to use floating point models in order to provide acceptable accuracy on realistic classification problems. However, working with floating point values significantly increases the HD computation cost. To address this issue, we proposed QuantHD, a novel framework for quantization of HD computing model during training. QuantHD enables HD computing to work with a low-cost quantized model (binary or ternary model) while providing a similar accuracy as the floating point model. We accordingly propose an FPGA implementation which accelerates HD computing in both training and inference phases. We evaluate QuantHD accuracy and efficiency on various real-world applications, and observe that QuantHD can achieve on average 17.2% accuracy improvement as compared to the existing binarized HD computing algorithms which provide a similar computation cost. In terms of efficiency, QuantHD FPGA implementation can achieve on average 42.3x and 4.7x (34.1x and 4.1x) energy efficiency improvement and speedup during inference (training) as compared to the state-of-the-art HD computing algorithms.