lyf's blog

what is TensorFlowTensors, in general, are simply arrays of numbers, or functions, that transform according to certain rules under a change of coordinates. TensorFlow is an open source software libr

PCA（Principal Component Analysis）是一种常用的数据分析方法。前面转了一篇关于PCA原理的文章，其中有些部分写的不是很清晰，因此做一个补充。方差和协方差下图是一个正态分布，均值和方差提供了对数据在特征空间的分布进行衡量的手段。如图所示，大部分的数据都分布在μ±3σ\mu\pm3\sigmaμ±3σ区间中。而方差的计算公式如下，σ(x,x)=E[(x−E(x)...

PCA（Principal Component Analysis）是一种常用的数据分析方法。PCA通过线性变换将原始数据变换为一组各维度线性无关的表示，可用于提取数据的主要特征分量，常用于高维数据的降维。数据的向量表示及降维问题一般情况下，在数据挖掘和机器学习中，数据被表示为向量。例如某个淘宝店2012年全年的流量及交易情况可以看成一组记录的集合，其中每一天的数据是一条记录，格式如下：(日期...

dFdX=[∂F∂ξ11∂F∂ξ12…∂F∂ξ1n⋮⋮⋮∂F∂ξn1∂F∂ξn2…∂F∂ξnn]\dfrac {d\mathbf{F}}{d\mathbf{X}}=\begin{bmatrix}\dfrac {\partial F}{\partial \xi_{11}} & \dfrac {\partial F}{\partial \xi_{12}} & \ld...

在利用梯度下降法对神经网络权重等参数进行训练时，需要利用反向传播去计算损失函数对权重参数的偏导数。反向传播下面分析是如何反向传播的(分析时不考虑偏置项)，参考上图，① 对于一个神经元jjj，它的输出被定义为，(1.1)Oj=φ(netj)=φ(∑k=1NwkjOk) O_j = \varphi(net_j)=\varphi(\sum_{k=1}^N w_{kj}O_k)...

To master Machine Learning (ML) one has to be good at maths, programming and domain knowledge. Domain knowledge (Eg: how to deal with images, audio, financial time series etc) changes from one class o...

在Ubuntu16.04上安装cuda时，报如下错误; Installing the NVIDIA display driver… The driver installation is unable to locate the kernel source. Please make sure that the kernel source packages are installed a...

持续….Linux-HA wiki Providing Open Source High-Availability Software for Linux and other Platforms.Getting Started with Linux-HA (heartbeat) Let me preface this document by saying most of this is not

AlphaGo后，是否接下来会有Alpha麻将？比较有意思。The world’s top Go player Lee Sedol reviews the match after the fourth match of the Google DeepMind Challenge Match against Google’s artificial intelligence program AlphaG

知乎原文。You only look once (YOLO) is a state-of-the-art, real-time objectdetection system. On a Pascal Titan X it processes images at 30 FPSand has a mAP of 57.9% on COCO test-dev.Yolo使用c和cuda实现...