共生混合神经网络看门狗异常检测
Symbiotic Hybrid Neural Network Watchdog For Outlier Detection
摘要:
神经网络在很大程度上是黑箱。被训练来对水果进行分类的神经网络可以将长颈鹿的图片分类为香蕉。一个神经网络看门狗的工作是识别这些输入,允许分类器忽略这些数据。我们研究看门狗是否应该从神经网络分离或共生连接。我们提出的经验证据表明,共生看门狗的性能优于当神经网络是不相交的。
英文摘要:
Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.
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。