arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.08087cs.LGcs.CV
收藏

基于计算的低成本同构机器学习模型图像分类算法的性能评估及应用

Performance evaluation and application of computation based low-cost homogeneous machine learning model algorithm for image classification

Amazon Web Services(亚马逊云科技)

W. H. Huang

摘要:

训练图像分类机器学习模型的目的是预测输入图像的类别。虽然有多种最先进的集成模型方法是公开可用的,但本文评估了一种低成本,简单算法的性能,该算法将无缝集成到现代生产级基于云的应用程序中。使用完整数据而不是数据子集训练的同质模型包含彼此不同的超参数和神经层。这些模型的推理将由新算法处理,该算法松散地基于条件概率理论。将对最终产出进行评价。

英文摘要:

The image classification machine learning model was trained with the intention to predict the category of the input image. While multiple state-of-the-art ensemble model methodologies are openly available, this paper evaluates the performance of a low-cost, simple algorithm that would integrate seamlessly into modern production-grade cloud-based applications. The homogeneous models, trained with the full instead of subsets of data, contains varying hyper-parameters and neural layers from one another. These models' inferences will be processed by the new algorithm, which is loosely based on conditional probability theories. The final output will be evaluated.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑