⏰

SocratesClub · Jul 27, 2024 · 9dcc87f · 9dcc87f
1 parent 230a57f
commit 9dcc87f
Show file tree

Hide file tree

Showing 13 changed files with 468 additions and 330 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/notebook/.ipynb_checkpoints/05-01-network-science-intro-checkpoint.ipynb b/notebook/.ipynb_checkpoints/05-01-network-science-intro-checkpoint.ipynb
diff --git a/notebook/.ipynb_checkpoints/05-02-networkx-checkpoint.ipynb b/notebook/.ipynb_checkpoints/05-02-networkx-checkpoint.ipynb
diff --git a/notebook/.ipynb_checkpoints/05-03-network-science-models-checkpoint.ipynb b/notebook/.ipynb_checkpoints/05-03-network-science-models-checkpoint.ipynb
@@ -28,7 +28,7 @@
    "source": [
     "<div><img src=img/net22.png width='1000px'></div>\n",
     "\n",
-    "# The random network model 随机网络模型\n"
+    "## The random network model 随机网络模型\n"
    ]
   },
   {
@@ -39,7 +39,7 @@
     }
    },
    "source": [
-    "# Erdös-Rényi model (1960)\n",
+    "## Erdös-Rényi model (1960)\n",
     "\n",
     "Definition: A random graph is a graph of N nodes where each pair of nodes is connected by probability p.\n",
     "\n",
@@ -58,7 +58,7 @@
     }
    },
    "source": [
-    "## To construct a random network:\n",
+    "### To construct a random network:\n",
     "- 1) Start with $N$ isolated nodes.\n",
     "- 2) Select a node pair and generate a random number between 0 and 1.\n",
     "If the number exceeds $p$, connect the selected node pair with a link,\n",
@@ -88,7 +88,7 @@
     }
    },
    "source": [
-    "## BINOMIAL DISTRIBUTION: MEAN AND VARIANCE\n",
+    "### BINOMIAL DISTRIBUTION: MEAN AND VARIANCE\n",
     "\n",
     "**二项分布**即重复n次独立的**伯努利试验**。\n",
     "\n",
@@ -130,7 +130,7 @@
     }
    },
    "source": [
-    "# In summary:\n",
+    "## In summary:\n",
     "- the number of links in a random network varies between realizations. \n",
     "- Its expected value is determined by **N** and **p**. \n",
     "- If we increase p a random network becomes denser: \n",
@@ -146,7 +146,7 @@
     }
    },
    "source": [
-    "# Degree Distribution\n",
+    "## Degree Distribution\n",
     "In a given realization of a random network some nodes gain numerous links, while others acquire only a few or no links. These differences are captured by the degree distribution, $p_k$. \n",
     "\n",
     "$p_k$ is the probability that a randomly chosen node has degree $k$. "
@@ -185,7 +185,7 @@
     }
    },
    "source": [
-    "# POISSON DISTRIBUTION\n",
+    "## POISSON DISTRIBUTION\n",
     "\n",
     "- Most real networks are **sparse**, meaning that for them $<k>$ ≪ N. \n",
     "- the degree distribution is well approximated by the Poisson distribution\n",
@@ -229,7 +229,7 @@
     }
    },
    "source": [
-    "# The small world phenomenon 小世界现象\n",
+    "## The small world phenomenon 小世界现象\n",
     "also known as **six degrees of separation**,\n",
     "has long fascinated the general public. It states that if you choose any two\n",
     "individuals anywhere on Earth, you will find a path of at most six acquaintances\n",
@@ -247,7 +247,7 @@
     }
    },
    "source": [
-    "# Consider a random network with average degree $<k>$. \n",
+    "## Consider a random network with average degree $<k>$. \n",
     "\n",
     "A node i in this network has on average:\n",
     "\n",
@@ -266,7 +266,7 @@
     }
    },
    "source": [
-    "# 从For循环的角度理解\n",
+    "## 从For循环的角度理解\n",
     "- 从这个节点i走一步，到达他/她的$<k>$个朋友\n",
     "- 从节点i走两步，先到他/她的$<k>$个朋友，再到每个朋友的$<k>$个朋友。\n",
     "- 。。。\n",
@@ -286,7 +286,7 @@
     }
    },
    "source": [
-    "# 随机网络的直径\n",
+    "## 随机网络的直径\n",
     "\n",
     ">  the expected number of nodes up to distance d from our starting node is $N(d)$ \n",
     "\n",
@@ -335,7 +335,7 @@
     }
    },
    "source": [
-    "# SIX DEGREES: EXPERIMENTAL CONFIRMATION\n",
+    "## SIX DEGREES: EXPERIMENTAL CONFIRMATION\n",
     "The first empirical study of the small world phenomena took place in 1967\n",
     "- Stanley Milgram, building on the work of Pool and Kochen, designed an experiment to measure the distances in social networks. \n",
     "- Milgram chose a stock broker in Boston and a divinity student in Sharon, Massachusetts as targets. \n",
@@ -355,7 +355,7 @@
    "source": [
     "Using Facebook’s social graph of May 2011, consisting of 721 million active users and 68 billion symmetric friendship links, researchers found:\n",
     "\n",
-    "# an average distance 4.74 between the users. \n",
+    "## an average distance 4.74 between the users. \n",
     "\n",
     "- Therefore, the study detected only ‘four degrees of separation’, closer to the prediction of than to Milgram’s six degrees.\n",
     "\n",
@@ -381,7 +381,7 @@
     }
    },
    "source": [
-    "# 大的聚集系数与小的网络直径如何并存？\n"
+    "## 大的聚集系数与小的网络直径如何并存？\n"
    ]
   },
   {
@@ -421,7 +421,7 @@
     }
    },
    "source": [
-    "# 邻居彼此认识吗？\n",
+    "## 邻居彼此认识吗？\n",
     "Local clustering coefficient\n",
     "\n",
     "We need to estimate the expected number of links $L_i$ between the node’s $k_i$ neighbors. \n",
@@ -441,7 +441,7 @@
     }
    },
    "source": [
-    "# 局部聚集系数\n",
+    "## 局部聚集系数\n",
     "\n",
     "$<C_i> = \\frac{<L>}{\\frac{1}{2} k_i(k_i - 1)} = p = \\frac{<k>}{N}$\n",
     "\n",
@@ -468,7 +468,7 @@
     }
    },
    "source": [
-    "# WS模型 （1998）\n",
+    "## WS模型 （1998）\n",
     "\n",
     "Duncan Watts and Steven Strogatz proposed an extension of the random network model motivated by two observations：\n",
     "- (a) Small World Property： In real networks the average distance between two nodes depends logarithmically on N\n",
@@ -534,7 +534,7 @@
     }
    },
    "source": [
-    "# In summary\n",
+    "## In summary\n",
     "- we find that the random network model does not capture the clustering of real networks. \n",
     "- Instead real networks have a **much higher clustering coefficient** than expected for a random network of similar N and L. \n",
     "- An extension of the random network model proposed by Watts and Strogatz [1998] addresses the coexistence of high <C> and the small world property. \n",
@@ -562,7 +562,7 @@
     }
    },
    "source": [
-    "# BA模型 （1999）\n",
+    "## BA模型 （1999）\n",
     "\n",
     "Barabasi (1999) Emergence of scaling in random networks.Science-509-12\n",
     "\n",
@@ -582,7 +582,7 @@
     }
    },
    "source": [
-    "# 无标度的意义"
+    "## 无标度的意义"
    ]
   },
   {
@@ -666,7 +666,7 @@
     }
    },
    "source": [
-    "# 无标度的意义\n",
+    "## 无标度的意义\n",
     "> ### 在网络中随机抽取一个节点的度可以显著的不同于平均度$<k>$\n",
     "\n",
     "上图最为直接的描绘出了这种特点，即与正态分布等相比，`无标度网络下降的慢`。\n",
@@ -716,7 +716,7 @@
     }
    },
    "source": [
-    "# 连续平均场\"Continuum Mean-Field\" \n",
+    "## 连续平均场\"Continuum Mean-Field\" \n",
     "\n",
     "\"Mean-Field\": many -> one\n",
     "\n",
@@ -737,7 +737,7 @@
     }
    },
    "source": [
-    "## 模型设定\n",
+    "### 模型设定\n",
     "* 初始状态有$m_0$个节点\n",
     "* 1. 增长原则：每次加入一个节点i （加入时间记为$t_i$）, 每个节点的加入带来m条边，2m个度的增加\n",
     "** 其中老节点分到的度数是m，新加入的那一个节点分到的度数为m.\n",
@@ -766,7 +766,7 @@
     }
    },
    "source": [
-    "## 度的增长/时间依赖性\n",
+    "### 度的增长/时间依赖性\n",
     "$k_i$在一个时间步获得一个度的概率表示为$\\prod (k_i) $， 那么有：\n",
     "\n",
     "$$\\prod (k_i)  = \\frac{k_i}{\\sum k_i} =  \\frac{k_i}{2mt}$$\n",
@@ -790,7 +790,7 @@
     }
    },
    "source": [
-    "## 积分结果\n",
+    "### 积分结果\n",
     "\n",
     "$k_i = C (2t) ^ {-0.5} $    （1）\n",
     "\n",
@@ -815,7 +815,7 @@
     }
    },
    "source": [
-    "## 累积概率分布\n",
+    "### 累积概率分布\n",
     "\n",
     "当我们思考一个累积概率分布的时候，我们想要的是$k_i(t) < k$的概率：$P(k_i(t) < k) $\n",
     "\n",
@@ -862,7 +862,7 @@
     }
    },
    "source": [
-    "# 参考文献\n",
+    "## 参考文献\n",
     "- Barabasi 2016 Network Science. Cambridge\n",
     "- Barabasi (1999) Emergence of scaling in random networks.Science-509-12.pdf\n",
     "- Barabasi (1999) Mean-field theory for scale-free random networks. PA.pdf\n",
@@ -900,7 +900,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.8.8"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,

diff --git a/notebook/.ipynb_checkpoints/08-05-transformer-checkpoint.ipynb b/notebook/.ipynb_checkpoints/08-05-transformer-checkpoint.ipynb
@@ -344,6 +344,47 @@
     "![image-2.png](./img/attention8.png)\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-07-24T12:15:19.223210Z",
+     "start_time": "2024-07-24T12:15:19.219011Z"
+    },
+    "slideshow": {
+     "slide_type": "slide"
+    }
+   },
+   "source": [
+    "## Hands-on Machine Learning \n",
+    "\n",
+    "\n",
+    "![image-2.png](./img/attention9.png)\n",
+    "\n",
+    "All the code examples in this book https://github.com/ageron/handson-ml3\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-07-24T12:15:19.223210Z",
+     "start_time": "2024-07-24T12:15:19.219011Z"
+    },
+    "slideshow": {
+     "slide_type": "slide"
+    }
+   },
+   "source": [
+    "## Dive into Deep Learning \n",
+    "\n",
+    "![image-2.png](./img/attention10.png)\n",
+    "\n",
+    "All the code examples in this book http://d2l.ai/\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {

diff --git a/notebook/01-intro2css.ipynb b/notebook/01-intro2css.ipynb
@@ -57,11 +57,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2021-07-23T08:39:12.575615Z",
-     "start_time": "2021-07-23T08:39:12.570247Z"
+     "end_time": "2024-07-27T00:58:59.873777Z",
+     "start_time": "2024-07-27T00:58:59.817394Z"
     },
     "cell_style": "center",
     "code_folding": [
@@ -942,7 +942,7 @@
  "metadata": {
   "celltoolbar": "幻灯片",
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -956,7 +956,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.8.8"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,