Yang不等式,Hölder不等式与闵可夫斯基(Minkowski)不等式

Yang不等式 ∀a,b≥0,p,q>0,∀a,b≥0,p,q>0,\forall a, b \ge 0, p, q\gt 0, 若 1p+1q=1,1p+1q=1,\dfrac{1}{p} + \dfrac{1}{q} = 1, 则: ab≤ap...

2017-10-29 22:22:33

阅读数 3371

评论数 0

gRPC

Protocol buffer data is structured as messages, where each message is a small logical record of information containing a series of name-value pairs c...

2018-08-21 17:13:03

阅读数 262

评论数 0

Deep Learning Notes: Chapter 1 Introduction

前言 最近开始读《Deep Learning》一书。这让我有了一个边读书边写笔记的动机:很有必要有一个笔记,能够让人很轻松流畅的读懂这本书的核心内容,至少可以把握住这本书的脉络。 由于终究是英文表达更地道,因此该笔记都是节选自书中的原文。各位读者如果有建议或意见,欢迎留言。谢谢! Deep ...

2018-08-18 20:16:48

阅读数 113

评论数 0

Pro Git Notes

Git is a Distributed Version Control Systems (DVCSs). Clients fully mirror of the repository, including its full history.

2018-08-12 01:38:23

阅读数 81

评论数 0

多元函数的牛顿迭代法

f(X)=f(X0)+f′(X0)ΔX+12(ΔX)Tf″(X0)ΔXf(X)=f(X0)+f′(X0)ΔX+12(ΔX)Tf″(X0)ΔXf(X) = f(X_0) + f'(X_0) \Delta X + \dfrac {1} {2} \left ( \Delta X \right ) ^T ...

2018-08-09 17:55:05

阅读数 2312

评论数 0

牛顿迭代法

若 x=F(x)x=F(x)x = F(x) 等价于 f(x)=0f(x)=0f(x) = 0 则F(x)F(x)F(x) 称为迭代函数。 f(x)f(x)f(x) 有二阶连续导数,且 f′(x)≠0f′(x)≠0f'(x) \neq 0 则 ∀x0,x∈R,∀x0,x∈R,\forall x_...

2018-08-09 09:02:05

阅读数 513

评论数 0

Nesterov Momentum

x_ahead = x + mu * v # evaluate dx_ahead (the gradient at x_ahead instead of at x) v = mu * v - learning_rate * dx_ahead x += v => x_pre...

2018-08-09 08:19:11

阅读数 448

评论数 0

CS231n Note

CS231n Note Concepts Concept Description Image Classification Object Detection Action Classification Image Caption...

2018-08-04 20:56:43

阅读数 130

评论数 0

Clockwise/Spiral Rule to parse C declaration

http://c-faq.com/decl/spiral.anderson.html

2018-05-01 18:32:17

阅读数 62

评论数 0

推荐系统

推荐方式 社会化推荐(social recommendation) 基于内容的推荐(content-based filtering) 协同过滤(collaborative filtering) 推荐系统评测 推荐系统试验方法 离线试验 用户调查 在线试验(AB测试) 评测指标...

2018-04-25 21:52:44

阅读数 122

评论数 0

机器学习的求导公式

机器学习的求导公式 损失函数的求导公式 设 loss(X)loss⁡(X)\operatorname {loss} \left (X\right ) 为单个样本 XXX 的损失函数, A=g(Z)=⎛⎝⎜⎜g(z1)⋮g(zn)⎞⎠⎟⎟A=g(Z)=(g⁡(z1)⋮g⁡(zn))A = g...

2018-04-18 12:30:10

阅读数 297

评论数 2

Recurrent Neural Networks

Examples of Sequence Data Speech Recognition Music Generation Sentiment Classification DNA Sequence Analysis Machine Translation Video Activity Rec...

2018-04-16 06:28:37

阅读数 237

评论数 0

Neural Style Transfer

Concept Content C + Style S = Generated image G What are Deep ConvNet Learning? More abstract features in deeper layer. Cost Function loss...

2018-04-16 00:04:20

阅读数 107

评论数 0

Face Recognition

Face Verification vs Face Recognition Name Input Output Description Face Verification Image and Name / ID Is the image the perso...

2018-04-15 19:39:30

阅读数 239

评论数 0

Object Detection

Concepts Name Description yyy Object Classification At most one object y=⎛⎝⎜c1c2c3⎞⎠⎟y=(c1c2c3)y = \begin{pmatrix} c_1 \\ c_2 \\ c...

2018-04-15 19:17:33

阅读数 83

评论数 0

Convolutional Neural Networks

Padding Output Dimension n+2p−f+1n+2p−f+1n + 2 p - f + 1 Padding Types Valid: p=0p=0p = 0 Same: n+2p−f+1=n⇒p=f−12n+2p−f+1=n⇒p=f−12n + 2 p - ...

2018-04-13 01:34:11

阅读数 103

评论数 0

Learning from Multiple tasks

Where Transfer Learning from A to B Makes Sense Task A and B have the same input X. You have a lot more data for A than B. Low level features in A ...

2018-04-12 23:37:42

阅读数 135

评论数 0

Bias and Variance with Mismatched Distributions

Bias and Variance with Mismatched Distributions

2018-04-12 22:08:00

阅读数 59

评论数 0

Softmax Function

Sigmoid Function sigmoid(z)=11−e−zsigmoid⁡(z)=11−e−z\operatorname {sigmoid} (z) = \dfrac {1} {1 - e ^{-z}} Softmax Function softmax(zi;Z)=ezi∑i=...

2018-04-11 22:13:26

阅读数 93

评论数 1

Momentum, RMSprob and Adam

Gradient Descent with Momentum Compute exponentially weighed average of gradient, and use the gradient to update weights. Algorithm On iteration...

2018-04-11 02:03:54

阅读数 140

评论数 0

提示
确定要删除当前文章?
取消 删除