SynergicLearning: neural network-based feature extraction for highly-accurate hyperdimensional learning
SynergicLearning: neural network-based feature extraction for highly-accurate hyperdimensional learning
复制标题
SynergicLearning：基于神经网络的特征提取，用于高精度超维学习
DOI：
10.1145/3400302.3415696
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Pedram, Massoud
中科院分区：
文献类型：
--
作者：
Nazemi, Mahdi;Fayyazi, Arash;Esmaili, Amirhossein;Pedram, Massoud
机器学习模型在准确性、计算/内存复杂性、训练时间和适应性等方面有所不同。例如，神经网络（NN）因其自动特征提取的质量而以其高精度而闻名，而大脑启发的多维（HD）学习模型则以其快速训练，计算效率和适应性而闻名。这项工作提出了一种混合的，协同的机器学习模型，擅长于所有上述特征，适合于增量，在线学习的芯片。该模型包括一个NN和一个分类器。NN充当特征提取器，并且经过专门训练以与采用HD计算框架的分类器良好地工作。这项工作还提出了一个参数化的硬件实现所述的特征提取和分类组件，同时引入一个编译器，映射任何任意NN和/或分类到上述硬件。所提出的混合机器学习模型具有与NN相同的精度水平（即±1%），同时与HD学习模型相比，精度至少提高了10%。此外，与最先进的高性能高清学习实现相比，混合模型的端到端硬件实现将功率效率提高了1.60倍，同时将延迟提高了2.13倍。这些结果对协同模型在挑战性认知任务中的应用具有深远的意义。
Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. ±1%) as NNs while achieving at least 10% improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.