Object recognition with gradient-based learning
Object recognition with gradient-based learning
复制标题
DOI：
10.1007/3-540-46805-6_19
复制
发表时间：
1999-01-01
期刊：
影响因子：
--
通讯作者：
Bengio, Y
中科院分区：
文献类型：
--
作者：
LeCun, Y;Haffner, P;Bengio, Y
在形状识别系统的设计中，寻找一组合适的特征是一个基本问题。本文试图表明，对于识别具有高度形状可变性的简单对象（如手写字符），直接向系统提供最低限度处理的图像并依靠学习来提取正确的特征集是可能的，甚至是有利的。卷积神经网络被证明特别适合这项任务。我们还表明，这些网络可以用来识别多个对象，而不需要显式分割的对象从他们的周围。本文的第二部分介绍了图形Transformer网络模型，该模型将基于梯度的学习的适用性扩展到使用图形来表示特征、对象及其组合的系统。
Finding an appropriate set of features is an essential problem in the design of shape recognition systems. This paper attempts to show that for recognizing simple objects with high shape variability such as handwritten characters, it is possible, and even advantageous, to feed the system directly with minimally processed images and to rely on learning to extract the right set of features. Convolutional Neural Networks are shown to be particularly well suited to this task. We also show that these networks can be used to recognize multiple objects without requiring explicit segmentation of the objects from their surrounding. The second part of the paper presents the Graph Transformer Network model which extends the applicability of gradient-based learning to systems that use graphs to represents features, objects, and their combinations.