上一页 1 ··· 152 153 154 155 156 157 158 159 160 ··· 189 下一页
摘要: airlock 阅读全文
posted @ 2017-09-28 11:46 papering 阅读(224) 评论(0) 推荐(0)
摘要: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/funcZone_TKDE_Zheng.pdf Specifically, we introduce the concept of Latent Activity 阅读全文
posted @ 2017-09-27 22:24 papering 阅读(201) 评论(0) 推荐(0)
摘要: http://mp.weixin.qq.com/s/2NoYnwE_FxfhU9qCwH-nnA 用实际轮廓确定商圈的范围 阅读全文
posted @ 2017-09-27 21:57 papering 阅读(210) 评论(0) 推荐(0)
摘要: https://en.wikipedia.org/wiki/Frobenius_inner_product Frobenius norm 阅读全文
posted @ 2017-09-27 20:01 papering 阅读(1549) 评论(0) 推荐(0)
摘要: In many cases, the smallness of the residual means that the approximation is close to the solution, i.e., 残差:结果的差值 误差:近似解与解的差值 https://en.wikipedia.or 阅读全文
posted @ 2017-09-27 19:51 papering 阅读(513) 评论(0) 推荐(0)
摘要: http://djt.qq.com/article/view/16 其主要思想就是把影响集中到一个点,然后再发散到一个面,出现意外情况后很容易就回退。 Gmail Labs是一个新特性橱窗,用户可以自己选择一些未正式发布的新特性进行体验,不喜欢可以关闭,在这个过程中,吃了螃蟹,也当了Google的小 阅读全文
posted @ 2017-09-27 17:41 papering 阅读(215) 评论(0) 推荐(0)
摘要: http://www.mit.edu/~9.520/scribe-notes/cl7.pdf https://en.wikipedia.org/wiki/Bayesian_interpretation_of_kernel_regularization the degree to which inst 阅读全文
posted @ 2017-09-27 15:58 papering 阅读(312) 评论(0) 推荐(0)
摘要: 适定性问题 zh.wikipedia.org/wiki/適定性問題 数学术语适定性问题来自于哈达玛所给出的定义。他认为物理现象中的数学模型应该具备下述性质: 适定性问题的原型范例包括对于拉普拉斯方程的狄利克雷问题,以及给定初始条件的热传导方程式。在物理过程中解决的这些问题,也许被视为“自然”问题。相 阅读全文
posted @ 2017-09-27 15:10 papering 阅读(1715) 评论(0) 推荐(0)
摘要: zh.wikipedia.org/wiki/數值微分 数值微分是数值方法中的名词,是用函数的值及其他已知资讯来估计一函数导数的算法。 http://mathworld.wolfram.com/NumericalDifferentiation.html Numerical differentiatio 阅读全文
posted @ 2017-09-27 14:05 papering 阅读(465) 评论(0) 推荐(0)
摘要: http://docs.oracle.com/cd/E19957-01/806-3568/ncg_goldberg.html 阅读全文
posted @ 2017-09-27 13:55 papering 阅读(222) 评论(0) 推荐(0)
摘要: http://ufldl.stanford.edu/tutorial/supervised/OptimizationStochasticGradientDescent/ 阅读全文
posted @ 2017-09-27 12:08 papering 阅读(187) 评论(0) 推荐(0)
摘要: https://stats.stackexchange.com/questions/164876/tradeoff-batch-size-vs-number-of-iterations-to-train-a-neural-network It has been observed in practic 阅读全文
posted @ 2017-09-27 11:47 papering 阅读(241) 评论(0) 推荐(0)
摘要: https://ipfs.io/ipfs/QmXoypizjW3WknFiJnKLwHCnL72vedxjQkDDP1mXWo6uco/wiki/Convex_function.html Every norm is a convex function, by the triangle inequal 阅读全文
posted @ 2017-09-27 11:05 papering 阅读(273) 评论(0) 推荐(0)
摘要: http://mathworld.wolfram.com/Moore-PenroseMatrixInverse.html 显然,埃尔米特矩阵主对角线上的元素都是实数的,其特征值也是实数。对于只包含实数元素的矩阵(实矩阵),如果它是对称阵,即所有元素关于主对角线对称,那么它也是埃尔米特矩阵。也就是说, 阅读全文
posted @ 2017-09-27 09:14 papering 阅读(1177) 评论(0) 推荐(0)
摘要: https://rdipietro.github.io/friendly-intro-to-cross-entropy-loss/ 【将输入转化为输出:概率分布】 When we develop a model for probabilistic classification, we aim to 阅读全文
posted @ 2017-09-26 21:00 papering 阅读(259) 评论(0) 推荐(0)
摘要: https://en.wikipedia.org/wiki/Claude_Shannon In 1948, the promised memorandum appeared as "A Mathematical Theory of Communication," an article in two 阅读全文
posted @ 2017-09-26 19:48 papering 阅读(197) 评论(0) 推荐(0)
摘要: http://cs231n.github.io/linear-classify/ 阅读全文
posted @ 2017-09-26 19:23 papering 阅读(173) 评论(0) 推荐(0)
摘要: every row of W is a classifier for one of the classes As we saw above, every row of W is a classifier for one of the classes. The geometric interpreta 阅读全文
posted @ 2017-09-26 16:18 papering 阅读(237) 评论(0) 推荐(0)
摘要: The hinge loss is a convex function, so many of the usual convex optimizers used in machine learning can work with it. It is not differentiable, but h 阅读全文
posted @ 2017-09-26 15:42 papering 阅读(405) 评论(0) 推荐(0)
摘要: http://www1.inf.tu-dresden.de/~ds24/lehre/ml_ws_2013/ml_11_hinge.pdf Two extremes: • Big 𝐶 → the loss is more important → better recognition rate but 阅读全文
posted @ 2017-09-26 15:35 papering 阅读(324) 评论(0) 推荐(0)
摘要: 图灵的基本思想 图灵的基本思想是用机器来模拟人们用纸笔进行数学运算的过程,他把这样的过程看作下列两种简单的动作: 在纸上写上或擦除某个符号; 把注意力从纸的一处移动到另一处; 而在每个阶段,人要决定下一步的动作,依赖于(a)此人当前所关注的纸上某个位置的符号和(b)此人当前思维的状态。 在可计算性理 阅读全文
posted @ 2017-09-26 14:04 papering 阅读(924) 评论(0) 推荐(0)
摘要: crf 阅读全文
posted @ 2017-09-26 12:17 papering 阅读(131) 评论(0) 推荐(0)
摘要: http://mathworld.wolfram.com/FrobeniusNorm.html 阅读全文
posted @ 2017-09-26 10:49 papering 阅读(203) 评论(0) 推荐(0)
摘要: https://en.wikipedia.org/wiki/Norm_(mathematics) http://cs231n.github.io/classification/ 阅读全文
posted @ 2017-09-26 10:23 papering 阅读(265) 评论(0) 推荐(0)
摘要: 输入 输出 的中间 阅读全文
posted @ 2017-09-25 22:43 papering 阅读(206) 评论(0) 推荐(0)
摘要: 卷积定理是处理信号的重要工具:时域中的卷积等同于频域中的乘积。这意味着我们可以通过傅里叶变换将复杂的卷积运算简化为简单的乘法 卷积是现代科技(尤其是 AI 和图像处理)的基石: 图像处理:使用特定的卷积核(如 3x3 矩阵)对图像进行扫描,可以实现边缘检测、模糊处理或锐化效果。 深度学习 (CNN) 阅读全文
posted @ 2017-09-25 22:03 papering 阅读(435) 评论(0) 推荐(0)
摘要: C:\Python36\python.exe D:/pymine/clean/chained_located/chained_located_dynamic_input.py '-69,-47,,,-72,-40,-37,-96,-36,-97,-67,-67,-43,,-100,-70,-54,-62,-92,-98,,-33,-77,-17,-17,,-98,-76... 阅读全文
posted @ 2017-09-25 18:13 papering 阅读(325) 评论(0) 推荐(0)
摘要: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture9.pdf The deeper model performs worse, but it’s not caused by overfitting! 阅读全文
posted @ 2017-09-25 16:12 papering 阅读(301) 评论(0) 推荐(0)
摘要: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture4.pdf 阅读全文
posted @ 2017-09-25 14:19 papering 阅读(143) 评论(0) 推荐(0)
摘要: http://cs231n.github.io/linear-classify/ http://cs231n.github.io/assets/svmvssoftmax.png 阅读全文
posted @ 2017-09-25 11:28 papering 阅读(226) 评论(0) 推荐(0)
摘要: 直观 阅读全文
posted @ 2017-09-22 16:16 papering 阅读(143) 评论(0) 推荐(0)
摘要: http://www.cmo.com/features/articles/2016/3/9/data-decisions-dsp-vs-dmp.html As marketers assess their requirements for marketing technology, the ques 阅读全文
posted @ 2017-09-20 17:11 papering 阅读(304) 评论(0) 推荐(0)
摘要: http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/ 阅读全文
posted @ 2017-09-20 17:01 papering 阅读(207) 评论(0) 推荐(0)
摘要: https://www.tensorflow.org/tutorials/image_recognition 阅读全文
posted @ 2017-09-20 16:55 papering 阅读(257) 评论(0) 推荐(0)
摘要: http://neuralnetworksanddeeplearning.com/chap1.html Up to now, we've been discussing neural networks where the output from one layer is used as input 阅读全文
posted @ 2017-09-20 16:26 papering 阅读(271) 评论(0) 推荐(0)
摘要: http://neuralnetworksanddeeplearning.com/chap1.html . Sigmoid neurons are similar to perceptrons, but modified so that small changes in their weights 阅读全文
posted @ 2017-09-20 15:18 papering 阅读(322) 评论(0) 推荐(0)
摘要: spike 阅读全文
posted @ 2017-09-19 20:33 papering 阅读(191) 评论(0) 推荐(0)
摘要: @Matthew 【[抱拳]】推荐系统中,传统的两大算法,无论是基于人的过滤,还是基于物品的过滤,在前期历史数据的量和质都不充足的情况下,这两种传统的算法都无法冷启动。 【基于ANN的一种解决办法】 张三第一次点击了汽车广告,通过ANN训练,使得输出层的汽车的概率最大,次之的就为接下来要投出的广告类 阅读全文
posted @ 2017-09-19 20:28 papering 阅读(242) 评论(0) 推荐(0)
摘要: BLEU is designed to approximate human judgement at a corpus level, and performs badly if used to evaluate the quality of individual sentences. https:/ 阅读全文
posted @ 2017-09-19 18:36 papering 阅读(263) 评论(0) 推荐(0)
摘要: 安装TensorFlow 包依赖 https://www.tensorflow.org/tutorials/layers Building the CNN MNIST Classifier 【Each of these methods accepts a tensor as input and re 阅读全文
posted @ 2017-09-19 18:10 papering 阅读(553) 评论(0) 推荐(0)
上一页 1 ··· 152 153 154 155 156 157 158 159 160 ··· 189 下一页