Neural_Network
Perceptons(感知机)
input is 0 or 1, output is 0 or 1. + threshold
value(阈值) + weights(权重) + bias(偏置) : measure of how easy it is to
get the perceptron to output a 1
Activation Function
sigmoid neuron.
sigmoid neuron
Just like a perceptron, the sigmoid neuron has
inputs, x1,x2,… . But instead of being just 0 or 1 , these inputs can
also take on any values between 0 and 1 . So, for instance, 0.638… is a
valid input for a sigmoid neuron. Output is between 0 and 1.
\[
\begin{eqnarra ...
Breadth-First Search(BFS)
It is a graph search algorithm that starts from a given node and explores the graph by expanding the nodes at the current depth before moving on to the next depth. BFS is useful for solving problems such as finding the shortest path between two nodes, determining the order in which nodes should be processed, and identifying cycles in a graph.
Software Engineering
Some notebooks of Software Engineering
linear System
Conclusion
Introduction to Design of
System
Performance Specification(性能规范)
Time domain and Frequency
domain
Fourier Transform
\[
\begin{array}{c}
X_{k}=\sum_{n=0}^{N-1} x_{n} \cdot e^{-i 2 \pi k n / N} \\
\\
x_{n}=\frac{1}{N} \sum_{k=0}^{N-1} X_{k} \cdot e^{i 2 \pi k n / N}
\end{array}
\]
Pygame(1)
Pygame Document
鹏城历险记
考完雅思后改了改简历投了一下，在经历了一个多月的5次面试后终于是混到了华为OD的一份offer。定在了5月26号在深圳入职。
5月28日
刚来第3天就收到了任总的端午礼盒，属实有点受宠若惊
5月29日
收到了小高的投喂
6月2日
拿到了第一份菊厂的宵夜，赛百味+车厘子+特仑苏，针不戳！
6月3日
端午放假第一天，到吴总家一起恰了顿饭
6月4日
踩着滑板在深圳湾公园兜了一圈，还去马哥的滨海大厦望了望。
6月9号
早上6点，被窗外的阳光照醒了，阳光洒在滑板上还挺好看。
Machine learning--数学相关（2）
Vector Spaces(向量空间)
Groups（群）
Consider a set \(\mathcal{G}\) and
an operation \(\otimes: \mathcal{G} \times
\mathcal{G} \rightarrow \mathcal{G}\) defined on \(\mathcal{G}\). Then \(G:=(\mathcal{G}, \otimes)\) is called a
group if the following hold:
1. Closure of \(\mathcal{G}\) under
\(\otimes: \forall x, y \in \mathcal{G}: x
\otimes y \in \mathcal{G}\)
2. Associativity: \(\forall x, y, z \in
\mathcal{G}:(x \otimes y) \otimes z=x \otimes(y \otimes
z)\)
3. Neutral element: \(\exists ...
多线程爬虫
记录一下requests多线程运行时的一个模板，同时有代理ip池使用的策略
M. Omair Ahmad's artical(2)
A Deep Light-Weight Image Super Resolution Network Using Multi-Scale Spatial and Morphological Feature Generating Residual Blocks
M. Omair Ahmad's artical(1)
A Low-Complexity Modified ThiNet Algorithm for Pruning Convolutional Neural Networks
