Giter VIP home page Giter VIP logo

basic-deeplearning's Introduction

Learn Deeplearning with NO Basic Knowledge

Chapter 01 Perception

本算法实现了最简单的感知器算法,可以实现and or not等基本计算,但是感知器模型对与线性不可分的数据是无能为力的。例如,感知器算法是无法计算异或操作。

Chapter 02 Linear Regression

本算法实现了线性回归算法。如果假设数据误差符合高斯分布,那么对数据进行最大似然估计,进行最优化求值和采用均方损失函数,进行最优化求值得到的是相同的结果,都是最小二乘估计。

Chapter 03 NeuralNetwork

本算法实现了全链接神经网络,网络大体被分为NeuralNetwork、Layer、Connections、Node、Connection几个类,以及校验工具箱ToolBox。
Network:整个神经网络的整体框架,包含若干Layer,主要进行训练,预测。
Layer:神经网络的某一层,包含若干节点。
Connections:所有的Connection的集合。
Connection:链接各个Node。
Node:神经网络中的各节点。
excerise:里面包含以Yann的手写识别数据库中的数字识别为样本,进行测试。

Chapter 04 Vector Programming

本算法根据向量化编程的思路,对上一节的全连接神经网络进行重写。本节代码中使用了numpy等类库。

Chapter 05 Convolutional Neural Network

本章介绍了卷积神经网络,通常卷积神经网络会和全连接神经网络混合使用,前面若干层分别是不同尺寸,不同功能的卷积核,进行卷积计算,然后伴随若干个全连接神经网络,进行softmax分类。
此处的BP算法,根据输出值,按照全连接网络里面的反向传播算法,进行梯度下降。到达卷积层时,按照本章的pooling和convolutionalLayer里面定义的方法进行反向传播。以全连接层计算出的损失作为卷基层的input_array,进行后续计算。具体推到,参照image文件夹下的图片。

Chapter 06 Recurrent Neural Network

本章介绍了循环神经网络,每一个层共享一组W和U权值。假设当前层处于第t时刻的第l层,想要前向计算O(t,l+1)输出,则计算等于WO(t-1, l+1) + UO(t, l)。在同一层,共享一组W和U权重。具体推到公式,参见image文件见下的图片

Chapter 07 LSTM

本章介绍了LSTM算法,通过增加遗忘门,输出门和输出门进行优化循环神经网络,以避免梯度消失或者梯度爆炸问题。具体数学证明见Image下。

Chapter 08 Recursive Neural Network

本章介绍了递归神经网络,递归神经网络在一定程度上解决了语法树的问题。公式推到见Image文件夹。

Reference

https://www.zybuluo.com/hanbingtao/note/433855 https://www.zybuluo.com/hanbingtao/note/448086 https://www.zybuluo.com/hanbingtao/note/476663 https://www.zybuluo.com/hanbingtao/note/485480 https://www.zybuluo.com/hanbingtao/note/541458 https://www.zybuluo.com/hanbingtao/note/581764 https://www.zybuluo.com/hanbingtao/note/626300

Concat and Email

email: [email protected] id: viekie

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.