Coder Social home page Coder Social logo

gitycc / tensorflow_tutorial Goto Github PK

View Code? Open in Web Editor NEW
30.0 4.0 26.0 13.11 MB

Step by step, Let you learn how to use tensorflow in practical.

Home Page: https://www.ycc.idv.tw/tag/tensorflow.html

Jupyter Notebook 95.91% Python 4.09%
machine-learning neurel-network deep-learning tensorflow

tensorflow_tutorial's Introduction

實作Tensorflow系列教程

一步一腳印的學Tensorflow

我想完成一套Tensorflow教程,將Deep Learning一些重要的概念一一的點出來,並且使用Tensorflow來實現或驗證這些概念。本教程有三個面向我希望做到的,我希望觀念講解時可以深入淺出,我希望呈現程式碼時可以結構嚴謹,我希望可以完整呈現Tensorflow的實用面。

本教程「網頁版」請至我的個人網站查看:http://www.ycc.idv.tw/tag__實作Tensorflow/

Ch01 Simple Logistic Classification on MNIST

建立一個簡單的單層Neurel Network。

Simple Neurel Network

Ch02 Build First Deep Neurel Network (DNN)

開始建立第一個Deep Learning,並仔細介紹Deep Learning的重要組成,包括:Hidden Layer、Activation Function、Mini-Batch Gradient Descent、Weight Regularization、Dropout和Optimizer。

DNN

Ch03 Build First Convolutional Neurel Network (CNN)

介紹影像處理上最廣為人使用的Convolutional Neurel Network,引入Convolution Layer和Pooling Layer的概念,並在最後完成最簡單的CNN架構:LeNet5。

CNN

Ch04 Autoencoder

建立一個DNN的Autoencoder,揭露Embedding Code的神奇效果,藉由壓縮與還原找出一個精簡描述一群數據的Embedding空間,在這空間上數據不需要人為給予Labels,機器會自行分類成為一個個合理的群體,所以Autoencoder可以用於Unsupervised Learning上。

Autoencoder

Embedding Code

Ch05 Word2Vec

介紹兩種Word2Vec模型:Skip-gram和CBOW,揭露Embedding Vector的神奇效果,利用壓縮上下文的關係,我們可以建立一個Embedding的空間,在這個空間語意相近的兩個字,它們的Embedding Vector也會彼此相似。

word2vec

Embedding Vector

CH06 Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)

介紹具有時序性的Neurel Network—RNN,並點出一般簡易型的RNN因為共用權重以及等效於非常深的網路,會遇到的梯度爆炸與梯度消失問題。LSTM是另外一種型態的RNN,利用建立「長期記憶」來避免梯度消失問題,至於梯度爆炸問題則可以使用Gradient Clipping的手法解決。

LSTM

tensorflow_tutorial's People

Contributors

gitycc avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

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.