## A glimpse of Markov property

Markov property is a core property in Markov Process, understanding it will give you a broader horizon on Reinforcement Learning. It’s simple that Markov Process doesn’t care about the past, however it is the past that definite the present, which means present is the outcome of the past. Nevertheless, the only thing we should do is focus on the present, because the present will be the past.

So, what we should take into consideration? Remembering all the past is not a ideal method, we should summarize them. From Sutton’s book “What we would like, ideally, is a state signal that summarize past sensation compactly, yet in such a way that all relevant information is retained. … A state signal that succeeds in retaining all relevant information is said to be Markov, or to have Markov property.”

## TensorFlow修炼手册（2）——模型的保存和恢复

TensorFlow中，利用TensorFlow训练好了模型之后，我们需要保存模型参数，然后加入到产品当中，这样，当有新的数据来了之后，算法不用重新训练，而是利用训练好的模型的参数，这样，即使是浏览器也可以写JavaScript跑深度学习的应用了。总的来说，我们需要创建tf.train.Saver对象的实例来调用saverestore两个方法分别来保存和恢复模型。通过学习总结如下

# 模型的保存

word2vec的网络结构

## LeNet的Tensorflow实现

LetNet是Yann Lecun教授开发的一种使用卷积神经网络的手写识别网络，其训练数据是MNIST。网络的结构如下图所示

TensorFlow

## 卷积神经网络（1）——基本概念

• 卷积层
• Local receptive fields
• Patch/Kernel/Filter
• Width
• Depth
• Stride
• Shared weights（共享权重）
• Feature map
• ReLU
• 池化层
• Pooling（池化/下采样）
• 全连接层（Full Connected Layer）

## Windows下安装xgboost库

xgboost是一个很强大的开源库，在Linux下安装还是很简单的，但是在Windows下安装比较麻烦一些，需要安装MinGW-w64，然后我们利用mingw32-make.exe编译器来编译xgboost

• 分类
• 准确率
• 召回率
• 精确率
• F1值
• 回归
• 平均绝对误差
• 均方误差
• R方