上一页 1 ··· 22 23 24 25 26 27 28 29 30 ··· 36 下一页
摘要: LeCun Y., Chopra S., Hadsell R., Ranzato M. & Huang F. A Tutorial on Energy-Based Learning. To appear in “Predicting Structured Data, 2006, 1: 0. 概 从能 阅读全文
posted @ 2020-11-29 10:50 馒头and花卷 阅读(313) 评论(0) 推荐(0)
摘要: Liu M., Tuzel O. Coupled Generative Adversarial Networks. NIPS, 2016. 概 用GAN和数据(从边缘分布中采样)来拟合联合分布. 主要内容 这篇文章想要解决的问题是, 在仅有俩组不同数据(即从各自边缘分布中采样的数据), 如何用GAN 阅读全文
posted @ 2020-11-28 17:53 馒头and花卷 阅读(323) 评论(0) 推荐(0)
摘要: Zhao J., Mathieu M. & LeCun Y. Energy-based generative adversarial networks. ICLR, 2017. 概 基于能量的一个解释. 主要内容 本文采用了与GAN不同的损失, 判别器$D$和生成器$G$分别最小化下面的损失: \[ 阅读全文
posted @ 2020-11-28 17:50 馒头and花卷 阅读(202) 评论(0) 推荐(0)
摘要: Chen X., Duan Y., Houthooft R., Schulman J., Sutskever I., Abbeel P. InfoGAN: Interpretable Representation Learning by Information Maximizing Generati 阅读全文
posted @ 2020-11-25 20:11 馒头and花卷 阅读(156) 评论(0) 推荐(0)
摘要: Huang J., Smola A., Gretton A., Borgwardt K. & Scholkopf B. Correcting Sample Selection Bias by Unlabeled Data. NIPS, 2007. 概 MMD量化了两组数据是否来自同一个分布的可能性, 阅读全文
posted @ 2020-11-19 20:11 馒头and花卷 阅读(997) 评论(0) 推荐(0)
摘要: Borgwardt K., Gretton A., Rasch M., Kriegel H., Schoikopf B., Smola A. Integrating structured biological data by Kernel Maximum Mean Discrepancy. 2006 阅读全文
posted @ 2020-11-19 18:00 馒头and花卷 阅读(751) 评论(0) 推荐(0)
摘要: Order Statistic The Order Statistic 所谓顺序统计量, 即一族独立的观测$X_1, X_2, \ldots, X_n$的排序后的产物 \[ X_{(1)} \le X_{(2)} \le \cdots \le X_{(n)}. \] 用大写的原因, 自然是我们可以将 阅读全文
posted @ 2020-11-16 10:17 馒头and花卷 阅读(784) 评论(0) 推荐(0)
摘要: [Chen T. & Li L. Intriguing Properties of Contrastive Losses. arXiv preprint arXiv 2011.02803, 2020.] 概 普通的对比损失有一种广义的表示方法, 改变alignment和distribution项的权 阅读全文
posted @ 2020-11-13 21:09 馒头and花卷 阅读(240) 评论(0) 推荐(0)
摘要: Croce F. & Hein M. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In International Conference on Ma 阅读全文
posted @ 2020-11-02 21:46 馒头and花卷 阅读(629) 评论(0) 推荐(0)
摘要: Pang T., Yang X., Dong Y., Xu K., Su H., Zhu J. Boosting Adversarial Training with Hypersphere Embedding. arXiv preprint arXIv 2002.08619 概 在最后一层, 对we 阅读全文
posted @ 2020-11-02 16:46 馒头and花卷 阅读(194) 评论(0) 推荐(0)
摘要: Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples Gowal S., Qin C., Uesato J., Mann T. & Kohli P. Uncovering the 阅读全文
posted @ 2020-11-01 21:28 馒头and花卷 阅读(229) 评论(0) 推荐(0)
摘要: Kim M., Tack J. & Hwang S. Adversarial Self-Supervised Contrastive Learning. In Advances in Neural Information Processing Systems, 2020. 概 这篇文章提出了对比学习 阅读全文
posted @ 2020-10-31 09:10 馒头and花卷 阅读(470) 评论(0) 推荐(0)
摘要: Wu Z., Xiong Y., Yu S. & Lin D. Unsupervised Feature Learning via Non-Parametric Instance Discrimination. arXiv preprint arXiv 1805.01978 概 这篇文章也是最近很虎 阅读全文
posted @ 2020-10-26 21:45 馒头and花卷 阅读(712) 评论(0) 推荐(0)
摘要: Hinton G., Vinyals O. & Dean J. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv 1503.02531 概 \[ q_1 = \frac{\exp(z_i/T)}{\sum_j \ex 阅读全文
posted @ 2020-10-26 09:54 馒头and花卷 阅读(241) 评论(0) 推荐(0)
摘要: Tian Y., Sun C., Poole B., Krishnan D., Schmid C. & Isola P. What Makes for Good Views for Contrastive Learning? arXiv preprint arXiv 2005.10243, 2020 阅读全文
posted @ 2020-10-24 21:43 馒头and花卷 阅读(491) 评论(0) 推荐(0)
摘要: 廖雪峰Git教程 初始化 在你想要git的文件夹内 git bash here 接着注册 git config --global user.name "XXXXXX" git config --global user.email "XXX@+++.com" 配置别名 git config --glo 阅读全文
posted @ 2020-10-23 09:34 馒头and花卷 阅读(82) 评论(0) 推荐(0)
摘要: Entropy, relative entropy and mutual information. Entropy $$ H(X) = -\sum_{x} p(x) \log p(x), $$ 熵非负, 且当且仅当$X$确定性的时候为有最小值0, 即$P(X=x_0)=1$. Proof: 由$\l 阅读全文
posted @ 2020-10-22 20:55 馒头and花卷 阅读(373) 评论(0) 推荐(0)
摘要: Keith Conrad. Stirling's Formula. Stirling's Formula \[ \lim_{n \rightarrow \infty} \frac{n!}{(n^n/e^n)\sqrt{2\pi n}} =1. \] Proof: \[ \begin{array}{l 阅读全文
posted @ 2020-10-15 12:10 馒头and花卷 阅读(151) 评论(0) 推荐(0)
摘要: Tian Y., Krishnan D., Isola P. CONTRASTIVE REPRESENTATION DISTILLATION. arXiv preprint arXiv 1910.10699, 2019. 概 感觉其和此的相似度有50%, 不过这篇写得早一点, 所以后者是借鉴了这篇文 阅读全文
posted @ 2020-10-10 20:49 馒头and花卷 阅读(791) 评论(0) 推荐(0)
摘要: Kang M., Park J. Contrastive Generative Adversarial Networks. arXiv preprint arXiv 2006.12681, 2020. 概 如何将对比损失和GAN结合在一起呢? 主要内容 还是老问题, 结合对比学习就是如何构造正负样本 阅读全文
posted @ 2020-10-09 20:23 馒头and花卷 阅读(434) 评论(0) 推荐(0)
上一页 1 ··· 22 23 24 25 26 27 28 29 30 ··· 36 下一页