神經(jīng)網(wǎng)絡(luò)的可解釋性綜述!
地址|https://zhuanlan.zhihu.com/p/368755357
本文僅作為學(xué)術(shù)分享,著作權(quán)歸屬原作者,侵刪
本文以 A Survey on Neural Network Interpretability 讀后感為主,加上自身的補(bǔ)充,淺談神經(jīng)網(wǎng)絡(luò)的可解釋性。
本文按照以下的章節(jié)進(jìn)行組織:
人工智能可解釋性的背景意義 神經(jīng)網(wǎng)絡(luò)可解釋性的分類 總結(jié)
01
解釋(Explanations),是指需要用某種語言來描述和注解
可解釋的邊界(Explainable Boundary),是指可解釋性能夠提供解釋的程度
可理解的術(shù)語(Understandable Terms),是指構(gòu)成解釋的基本單元
高可靠性的要求
倫理/法規(guī)的要求
作為其他科學(xué)研究的工具
02











featuremap_layout









03


參考
^“Extracting Decision Trees From Trained Neural Networks”. SIGKDD. July 23-26,2002 https://dl.acm.org/doi/10.1145/775047.775113
^ M. Wu, S. Parbhoo, M. C. Hughes, R. Kindle, L. A. Celi, M. Zazzi, V. Roth, and F. Doshi-Velez, “Regional tree regularization for interpretability in deep neural networks.” in AAAI, 2020, pp. 6413–6421. https://arxiv.org/abs/1908.04494
^K. Simonyan, A. Vedaldi, and A. Zisserman, “Deep inside convolutional networks: Visualising image classification models and saliency maps,” arXiv preprint arXiv:1312.6034, 2013.
^Q. Zhang, Y. Nian Wu, and S.-C. Zhu, “Interpretable convolutional neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
^P. W. Koh and P. Liang, “Understanding black-box predictions via influence functions,” in Proceedings of the 34th International Conference on Machine Learning-Volume 70, 2017.
^M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should i trust you?: Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016.
^M. Wojtas and K. Chen, “Feature importance ranking for deep learning,” Advances in Neural Information Processing Systems, vol. 33, 2020.
^Open Domain Dialogue Generation with Latent Images Z Yang, W Wu, H Hu, C Xu, Z Li - arXiv preprint arXiv:2004.01981, 2020 - arxiv.org https://arxiv.org/abs/2004.01981
——The End——
讀者,你好!我們建立了微信學(xué)習(xí)交流群,歡迎掃碼進(jìn)群討論!
微商、廣告無關(guān)人員請(qǐng)繞道!謝謝合作!


