Improving the Interpretability of Deep Neural Networks with Knowledge Distillation

• Published in: IEEE ... International Conference on Data Mining workshops pp. 905 - 912
• Main Authors: Liu, Xuan, Wang, Xiaoguang, Matwin, Stan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2018
• Subjects: Biological neural networks; dark knowledge; Data models; Decision Tree; Decision trees; interpretation; knowledge distillation; Knowledge engineering; Neural Networks; TensorFlow; Training; Visualization

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not enough to satisfy the needs of practical deployment where interpretability is demanded for cases involvin...