Shuzi_rank
不是因为看到希望才坚持,而是因为坚持才能看到希望
摘要: Game Theory Reveals the Future of Deep Learning Carlos E. Perez Deep Learning Patterns, Methodology and Strategy @ IntuitionMachine.com 译自:https://med 阅读全文
posted @ 2016-12-14 16:07 Shuzi_rank 阅读(2740) 评论(0) 推荐(0) 编辑
摘要: 译自:The Major Advancements in Deep Learning in 2016 建议阅读时间:10分钟 https://tryolabs.com/blog/2016/12/06/majoradvancementsdeeplearning2016/ 在过去的十多年来,深度学习一直 阅读全文
posted @ 2016-12-14 09:21 Shuzi_rank 阅读(740) 评论(0) 推荐(0) 编辑
摘要: (1) 运行create data,其中包括下载cifar10,并转换为hdf5格式(详见百度百科:http://baike.baidu.com/view/771949.htm#4_2): cifar10的数据简介见:http://www.cs.toronto.edu/~kriz/cifar.htm 阅读全文
posted @ 2016-12-06 19:25 Shuzi_rank 阅读(201) 评论(0) 推荐(0) 编辑
摘要: ~~~~~~~~~~~My problem is here~~~~~~~~~~~~~~~~~~~~~~ Error: Microsoft visual C++ 10.0 is required (unable to find vcvarsall.bat) %VS110COMNTOOLS%部分pyth 阅读全文
posted @ 2016-12-05 17:11 Shuzi_rank 阅读(3437) 评论(0) 推荐(0) 编辑
摘要: 选自《Reinforcement Learning: An Introduction》, version 2, 2016, Chapter2 https://webdocs.cs.ualberta.ca/~sutton/book/bookdraft2016sep.pdf 引言中是这样引出Chapte 阅读全文
posted @ 2016-12-01 11:23 Shuzi_rank 阅读(4129) 评论(0) 推荐(0) 编辑
摘要: 译自:Don't Interpret Linear Hidden Units, they do not exist! http://building-babylon.net/2016/10/19/dont-interpret-linear-hidden-units-they-dont-exist/ 阅读全文
posted @ 2016-10-21 17:12 Shuzi_rank 阅读(286) 评论(0) 推荐(0) 编辑
摘要: Multi-task Learning for Stock Selection Joumana Ghosn and Yoshua Bengio 摘要 用人工神经网络预测未来回报以便于做出对应的金融决策时,我们需要考虑是为每支stock训练一个独立的网络结构还是所有的stocks能够共享一个网络结构。 阅读全文
posted @ 2016-10-17 15:27 Shuzi_rank 阅读(628) 评论(0) 推荐(1) 编辑
摘要: It is important to note the distinction between time series and sequential data. In both cases, the data consist of a sequence, or list of values, in 阅读全文
posted @ 2016-09-02 19:42 Shuzi_rank 阅读(1427) 评论(0) 推荐(0) 编辑
摘要: 别看本文没有几页纸,本着把经典的文多读几遍的想法,把它彩印出来看,没想到效果很好,比在屏幕上看着舒服。若用蓝色的笔圈出重点,这篇文章中几乎要全蓝。字字珠玑。 Reducing the Dimensionality of Data with Neural Networks G.E. Hinton an 阅读全文
posted @ 2016-08-29 16:24 Shuzi_rank 阅读(2789) 评论(0) 推荐(0) 编辑
摘要: The Impact of Imbalanced Training Data for Convolutional Neural Networks Paulina Hensman and David Masko 摘要 本论文从实验的角度调研了训练数据的不均衡性对采用CNN解决图像分类问题的性能影响。C 阅读全文
posted @ 2016-08-22 14:24 Shuzi_rank 阅读(1157) 评论(0) 推荐(0) 编辑