Evaluating Deep Learning Biases Based on Grey-Box Testing Results
Evaluating Deep Learning Biases Based on Grey-Box Testing Results
复制标题
根据灰盒测试结果评估深度学习偏差
DOI：
10.1007/978-3-030-55180-3_48
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Patricia Morreale
中科院分区：
文献类型：
--
作者：
Juan Li;Thayssa Silva;Mira Franke;Moushume Hai;Patricia Morreale
令人兴奋和有前途的深度学习方法在处理大型真实的世界数据集方面非常成功，例如图像识别，语音识别和语言翻译。然而，许多研究发现，它在AI/ML技术的设计、生产、部署和使用中存在偏见。在本文中，我们首先从数学上解释了偏差的原因，然后提出了一种基于深度学习中神经元和自动编码器的测试结果来评估偏差的方法。我们的解释将每个神经元或自动编码器视为相似性测量的近似值，其中灰盒测试结果可用于测量偏差并找到减少偏差的方法。我们认为，监控深度学习网络的结构和参数是捕捉深度学习中偏差来源的有效方法。
The very exciting and promising approaches of deep learning are immensely successful in processing large real world data sets, such as image recognition, speech recognition, and language translation. However, much research discovered that it has biases that arise in the design, production, deployment, and use of AI/ML technologies. In this paper, we first explain mathematically the causes of biases and then propose a way to evaluate biases based on testing results of neurons and auto-encoders in deep learning. Our interpretation views each neuron or autoencoder as an approximation of similarity measurement, of which grey-box testing results can be used to measure biases and finding ways to reduce them. We argue that monitoring deep learning network structures and parameters is an effective way to catch the sources of biases in deep learning.