Interpretation of Neural Networks for Classification Tasks
Interpretation of Neural Networks for Classification Tasks
复制标题
分类任务的神经网络解读
DOI：
--
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
H. Gemmeke
中科院分区：
文献类型：
--
作者：
A. Bernatzki;W. Eppler;H. Gemmeke
为了克服神经网络的黑盒行为，人们提出了许多不同的方法。到目前为止，还没有能够处理通用前馈网络的标准工具。本文提出了一种将可视化技术与变换算法相结合来解释神经前馈网络的方法。在超声波裂纹检测中的应用将表明，克服神经网络的黑盒结构并不是学术性的。它表明训练后网络的优化是可能的并且具有很高的可用性。
To overcome the black box behaviour of neural networks many different approaches have been proposed. Up to now there is no standard tool being able to handle general feedforward networks. In this paper a method is proposed to combine visualization techniques with transformation algorithms to interpret neural feedforward networks. An application in ultrasonic crack detection will show that the overcoming of the black box structure of neural networks is not academical. It shows that the optimization of a network after training is possible and highly usable.