Convolution
Convolution
复制标题
DOI：
10.1007/978-3-030-15729-6_15
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Gopinath Rebala;A. Ravi;Sanjay Churiwala
中科院分区：
文献类型：
--
作者：
Gopinath Rebala;A. Ravi;Sanjay Churiwala
卷积是机器学习领域中一个非常重要的概念。在前面的许多章节中，您已经阅读了各种算法，并且看到了它们是如何处理数字的。卷积是一种自动提取和合成识别目标类所需的重要特征的技术，对机器学习应用非常有用。从根本上讲，卷积是以地面事实和代价函数为指导的特征工程。因此，卷积被用于机器学习中一些最酷的应用，如图像识别、手写识别、解读路标等。正如你很好地想象的那样，机器学习最著名的应用之一--ADAS(自主驾驶辅助系统)--依赖于卷积作为整个系统的一个组件来识别物体和解读标志！！
Convolution is a very important concept in the world of machine learning. In many of the previous chapters, you have read about various algorithms, and you have seen how they work on numbers. Convolution is a technique which automates extraction and synthesis of significant features needed to identify the target classes, useful for machine learning applications. Fundamentally, convolution is feature engineering guided by the ground truth and cost function. Thus, convolution is used for some of the coolest applications of machine learning, such as image recognition, handwriting reading, interpreting street signs, etc. As you can well imagine, one of the most famous applications of machine learning – ADAS (autonomous driver assistance system) – depends on convolution as a component of the whole system to identify objects and to interpret signs!!