博客
关于我
强烈建议你试试无所不能的chatGPT,快点击我
【推荐】Keras教程:Python深度学习超级入门指南
阅读量:7040 次
发布时间:2019-06-28

本文共 2222 字,大约阅读时间需要 7 分钟。

hot3.png

2016-11-27 机器学习研究会

点击上方“机器学习研究会”可以订阅哦

摘要

 

转自:爱可可-爱生活

In this step-by-step Keras tutorial, you’ll learn how to build a convolutional neural network in Python!

In fact, we’ll be training a classifier for handwritten digits that boasts over 99% accuracy on the famous MNIST dataset.
Before we begin, we should note that this guide is geared toward beginners who are interested in applied deep learning.
Our goal is to introduce you to one of the most popular and powerful libraries for building neural networks in Python. That means we’ll brush over much of the theory and math, but we’ll also point you to great resources for learning those.
Before we start...
Recommended Prerequisites

The recommended prerequisites for this guide are:

  • Understanding of essential machine learning concepts

  • Python programming skills

To move quickly, we'll assume you have this background.

Why Keras?

Keras is our recommended library for deep learning in Python, especially for beginners. Its minimalistic, modular approach makes it a breeze to get deep neural networks up and running. You can read more about it here:

The Keras library for deep learning in Python

 

WTF is Deep Learning?

Deep learning refers to neural networks with multiple hidden layers that can learn increasingly abstract representations of the input data. This is obviously an oversimplification, but it's a practical definition for us right now.

For example, deep learning has led to major advances in computer vision. We're now able to classify images, find objects in them, and even label them with captions. To do so, deep neural networks with many hidden layers can sequentially learn more complex features from the raw input image:

  • The first hidden layers might only learn local edge patterns.

  • Then, each subsequent layer (or filter) learns more complex representations.

  • Finally, the last layer can classify the image as a cat or kangaroo.

These types of deep neural networks are called Convolutional Neural Networks.

链接:
https://elitedatascience.com/keras-tutorial-deep-learning-in-python
原文链接:
http://weibo.com/1402400261/EjqMi6r7J?from=page_1005051402400261_profile&wvr=6&mod=weibotime&type=comment#_rnd1480235576335

转载于:https://my.oschina.net/Bettyty/blog/798699

你可能感兴趣的文章
(ext2,ext3,reiserfs,xfs,jfs)文件系统的性能测试
查看>>
tree
查看>>
c/c++笔记(不断更新)
查看>>
Linux的目录
查看>>
RMAN命令简解
查看>>
Linux 磁盘管理及基础命令使用
查看>>
FormsAuthentication.SetAuthCookie是必须写的吗?
查看>>
mysql编译报错
查看>>
Linux逻辑卷
查看>>
MySQL避免使用SWAP
查看>>
scp非交互式
查看>>
Cobbler全自动批量安装部署Linux系统
查看>>
Solaris 10 开启SSH
查看>>
我的友情链接
查看>>
iOS支付宝报错 rsa_private read error : private key is NULL
查看>>
给定两个整型变量的值,将两个值的内容进行交换
查看>>
Apache不记录指定类型日志
查看>>
Docker安装使用
查看>>
mysql性能及优化探讨
查看>>
cacti监控mongodb和redis
查看>>