|
用引导特征反演解释基于DNN的预测
Towards Explanation of DNN‑based Prediction with Guided Feature Inversion |
|
| |
| 课程网址: |
http://videolectures.net/kdd2018_du_DNN_based_prediction/
|
| 主讲教师: |
Mengnan Du
|
| 开课单位: |
德克萨斯农工大学
|
| 开课时间: |
2018-11-23
|
| 课程语种: |
英语
|
| 中文简介: |
虽然深度神经网络（DNN）已经成为一种有效的计算工具，但预测结果往往因缺乏可解释性而受到批评，而可解释性在健康信息学等许多现实世界应用中至关重要。基于局部解释的现有尝试旨在通过监测给定输入的邻域来识别对DNN的预测贡献最大的相关特征。他们通常只是简单地忽略DNN的中间层，这些中间层可能包含丰富的解释信息。为了弥补这一差距，在本文中，我们建议研究一种引导特征反演框架，以利用深层结构进行有效解释。所提出的框架不仅确定了每个特征在输入中的贡献，而且为DNN模型的决策过程提供了见解。通过在DNN的输出层与目标类别的神经元进一步交互，我们强制解释结果具有类别判别性。我们将所提出的解释模型应用于不同的CNN架构，为图像数据提供解释，并在ImageNet和PASCAL VOC07数据集上进行了广泛的实验。解释结果证明了我们提出的框架在为基于DNN的预测提供类别判别解释方面的有效性。
|
| 课程简介: |
While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics. Existing attempts based on local interpretations aim to identify relevant features contributing the most to the prediction of DNN by monitoring the neighborhood of a given input. They usually simply ignore the intermediate layers of the DNN that might contain rich information for interpretation. To bridge the gap, in this paper, we propose to investigate a guided feature inversion framework for taking advantage of the deep architectures towards effective interpretation. The proposed framework not only determines the contribution of each feature in the input but also provides insights into the decision-making process of DNN models. By further interacting with the neuron of the target category at the output layer of the DNN, we enforce the interpretation result to be class-discriminative. We apply the proposed interpretation model to different CNN architectures to provide explanations for image data and conduct extensive experiments on ImageNet and PASCAL VOC07 datasets. The interpretation results demonstrate the effectiveness of our proposed framework in providing class-discriminative interpretation for DNN-based prediction.
|
| 关 键 词: |
用引导特征反演解释; 基于DNN的预测; 深度神经网络; 引导特征反演框架
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2023-03-27：cyh
|
| 最后编审: |
2023-03-27：cyh
|
| 阅读次数: |
26
|
|
图 书 馆