原创 Max-Mahalanobis Linear Discriminant Analysis Networks
文章目錄概主要內容 Pang T, Du C, Zhu J, et al. Max-Mahalanobis Linear Discriminant Analysis Networks[C]. international conf
2020-07-06 13:57:45
1
原创 KKT (LICQ)
文章目錄基本內容LICQ 假設KKT 定理KKT定理的證明引理AFarkas 引理推論KKT定理的證明 H. E. Krogstad, TMA 4180 Optimeringsteori KARUSH-KUHN-TUCKER
2020-06-22 14:15:12
原创 Differential Evolution: A Survey of the State-of-the-Art
文章目錄概主要內容DE/rand/1/binDE/?/?/?DE/rand/1/expDE/best/1DE/best/2DE/rand/2超參數的選擇FFF的選擇NPNPNP的選擇CrCrCr的選擇一些連續變體ABCDEG一些缺
2020-06-22 11:32:46
原创 Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach
文章目錄概主要內容 Lam R, Willcox K, Wolpert D H, et al. Bayesian Optimization with a Finite Budget: An Approximate Dynamic
2020-06-22 11:32:46
原创 Geometric GAN
文章目錄概主要內容McGAN結合SVM訓練ζ\zetaζ訓練gθg_{\theta}gθ理論分析證明 Jae Hyun Lim, Jong Chul Ye, Geometric GAN. 概 很有趣, GAN的訓練過程可以分
2020-06-22 11:32:45
2
原创 Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
文章目錄概主要內容算法一些有趣的指標魯棒性定義合格的抗干擾機制代碼 Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, Ananthram Swami, Distilla
2020-06-22 11:32:45
原创 EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES
文章目錄概主要內容從線性談起非線性 Goodfellow I, Shlens J, Szegedy C, et al. Explaining and Harnessing Adversarial Examples[J]. arX
2020-06-22 11:32:45
4
原创 McGan: Mean and Covariance Feature Matching GAN
文章目錄概主要內容Mean Matching IPMprimedualCovariance Feature Matching IPMprimedual算法代碼 Mroueh Y, Sercu T, Goel V, et al.
2020-06-22 11:32:45
原创 Towards Evaluating the Robustness of Neural Networks
文章目錄概主要內容基本的概念目標函數如何選擇c如何應對Box約束L2L_2L2 attackL0L_0L0 attackL∞L_{\infty}L∞ attack Nicholas Carlini, David Wagne
2020-06-22 11:32:40
1
原创 DEEP DOUBLE DESCENT: WHERE BIGGER MODELS AND MORE DATA HURT
文章目錄概主要內容Effective Model Complexity(EMC)label noisedata augmentation下降方式SGD vs AdamAdamSGDSGD + Momentumearly-stopp
2020-06-22 11:32:40
3
原创 Generating Adversarial Examples with Adversarial Networks
文章目錄概主要內容black-box 拓展 Xiao C, Li B, Zhu J, et al. Generating Adversarial Examples with Adversarial Networks[J]. ar
2020-06-22 11:32:37
3
原创 AT-GAN: A Generative Attack Model for Adversarial Transferring on Generative Adversarial Nets
文章目錄概主要內容符號說明Original GeneratorTransfer the Generator Wang X., He K., Guo C., Weinberger K., Hopcroft H., AT-GAN:
2020-06-22 11:32:37
原创 ADAM : A METHOD FOR STOCHASTIC OPTIMIZATION
文章目錄概主要內容算法選擇合適的參數一些別的優化算法AdaMax理論代碼 Kingma D P, Ba J. Adam: A Method for Stochastic Optimization[J]. arXiv: Learn
2020-06-16 06:20:52
原创 IMPROVING ADVERSARIAL ROBUSTNESS REQUIRES REVISITING MISCLASSIFIED EXAMPLES
文章目錄概主要內容符號MART Wang Y, Zou D, Yi J, et al. Improving Adversarial Robustness Requires Revisiting Misclassified Exa
2020-06-16 06:20:52
2
原创 Universal adversarial perturbations
文章目錄概主要內容算法實驗部分實驗1實驗2實驗3代碼 Moosavidezfooli S, Fawzi A, Fawzi O, et al. Universal Adversarial Perturbations[C]. com
2020-06-16 06:20:52
1