Yudi Xie

Yudi Xie

Short biography for the left-hand sidebar

Blog posts

2024

ReID

less than 1 minute read

Published:

一些概念

LanguageModel

less than 1 minute read

Published:

语言模型

Sequence_Models

less than 1 minute read

Published:

现实中很多数据其实都有时序结构的

Precision_Recall

1 minute read

Published:

First of all

In machine learing, precision and recall are two standards to evaluate a model , but why precision and recall can make such a useful work? Here are the answers

Rare classification example

When we want to train a classifier to classify the disease on the patient, you train a classifier $f_{\vec{w},b}(\vec{x})$ ($y=1$ if disease present,$y=0$ otherwise)

ResNet

less than 1 minute read

Published:

函数训练时可能遇到的问题

DiffusionModel

1 minute read

Published:

INTRODUCTION

Divided into part procession , Diffusion Model has a “Forward Process” and a “Reverse Process”.

Pooling（池化层）

less than 1 minute read

Published:

引入

在之前我们对图像进行卷积操作时，例如检测边界 （0与1的边界） img

GAN笔记

less than 1 minute read

Published:

两个核心

Generator

img

debug a learning algorithm

less than 1 minute read

Published:

Look at this J funciton: \(J(\vec{w},b)=\frac{1}{2m}\sum^m_{i=1}(f_{\vec{m},b}\vec({x}^{(i)})-y^{(i)})^2+\frac{\lambda}{2m}\sum^n_{j=1}w^2_j\)

ML/Deep Learning Note4-卷积层

1 minute read

Published:

几个基础概念

1、Receptive Field(感受野)

在卷积神经网络中，感受野的定义是：卷积神经网络每一层输出的特征图（feature map）上的像素点在原始图像上映射的区域大小。

ML/Deep Learning Note4-交叉熵与KL散度

less than 1 minute read

Published:

昨晚被Johnny Zhu问了一下交叉熵是啥东西，发现自己确实是学了如学，只学了个名字，所以重新整理一下