Understand the key computations underlying deep learning, use them to build and train deep neural networks, and apply it to computer vision.

学习目标

  • See deep neural networks as successive blocks put one after each other
  • Build and train a deep L-layer Neural Network
  • Analyze matrix and vector dimensions to check neural network implementations.
  • Understand how to use a cache to pass information from forward propagation to back propagation.
  • Understand the role of hyperparameters in deep learning

【中文翻译】

  了解深层学习的关键计算, 利用它们构建和训练深层神经网络, 并将其应用于计算机视觉。

学习目标
  (1) 查看深层神经网络作为连续的块互相放在一起
  (2) 构建和训练层度为L的深层神经网络
  (3) 分析矩阵和向量维数以检查神经网络的实现。
  (4) 了解如何使用缓存将信息从正向传播传递到反向传播。
  (5) 理解超参数在深度学习中的作用
 
 
 

课程一(Neural Networks and Deep Learning),第四周(Deep Neural Networks)—— 0.学习目标的更多相关文章

  1. [C1W1] Neural Networks and Deep Learning - Introduction to Deep Learning

    第一周:深度学习引言(Introduction to Deep Learning) 欢迎(Welcome) 深度学习改变了传统互联网业务,例如如网络搜索和广告.但是深度学习同时也使得许多新产品和企业以 ...

  2. Deep Learning: Assuming a deep neural network is properly regulated, can adding more layers actually make the performance degrade?

    Deep Learning: Assuming a deep neural network is properly regulated, can adding more layers actually ...

  3. 吴恩达《深度学习》-第一门课 (Neural Networks and Deep Learning)-第四周:深层神经网络(Deep Neural Networks)-课程笔记

    第四周:深层神经网络(Deep Neural Networks) 4.1 深层神经网络(Deep L-layer neural network) 有一些函数,只有非常深的神经网络能学会,而更浅的模型则 ...

  4. Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Initialization)

    声明:所有内容来自coursera,作为个人学习笔记记录在这里. Initialization Welcome to the first assignment of "Improving D ...

  5. Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week2, Assignment(Optimization Methods)

    声明:所有内容来自coursera,作为个人学习笔记记录在这里. 请不要ctrl+c/ctrl+v作业. Optimization Methods Until now, you've always u ...

  6. Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Gradient Checking)

    声明:所有内容来自coursera,作为个人学习笔记记录在这里. Gradient Checking Welcome to the final assignment for this week! In ...

  7. Coursera Deep Learning 2 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization - week1, Assignment(Regularization)

    声明:所有内容来自coursera,作为个人学习笔记记录在这里. Regularization Welcome to the second assignment of this week. Deep ...

  8. 读《Deep Learning Tutorial》(台湾大学 李宏毅 深度学习教学ppt)后杂记

    原ppt下载:pan.baidu.com/s/1nv54p9R,密码:3mty 需深入实践并理解的重要概念: Deep Learning: SoftMax Fuction(输出层归一化函数,与sigm ...

  9. 【RS】Wide & Deep Learning for Recommender Systems - 广泛和深度学习的推荐系统

    [论文标题]Wide & Deep Learning for Recommender Systems (DLRS'16) [论文作者] Heng-Tze Cheng, Levent Koc, ...

随机推荐

  1. 含参变量积分-Leibniz法则

    定理3,5参考同济下册. 下面的求导-> 三重积分可以化为累次积分经过过2次累次积分后,三重积分对dt的导数形式就等价于定理3了

  2. flask中flash不显示

    需要在html文件中body中加入下列语句 <div class='container'> <div class="row"> {% with messag ...

  3. java经典40+分析

      现在是3月份,也是每年开年企业公司招聘的高峰期,同时有许多的朋友也出来找工作.现在的招聘他们有时会给你出一套面试题或者智力测试题,也有的直接让你上机操作,写一段程序.算法的计算不乏出现,基于这个原 ...

  4. VSCode的终端修改

    快速打开VSCode的快捷键是:Ctrl + `(反引号) 转自:https://blog.csdn.net/u013517122/article/details/82776607 因本人实在忍受不了 ...

  5. 学以致用五----centos7+python3.6.2+django2.1.1

    目的,在python 3.6的基础上搭建 django 2.x 一.使用pip安装django ,但是使用pip命令的时候报错,解决方法,做软连接 ln -s /usr/local/python/bi ...

  6. LoadIcon

    1.LoadIcon(HINSTANCE hInstance,LPCSTR lpIconName);该函数从与 hInstance 模块相关联的可执行文件中装入lpIconName指定的图标资源,仅当 ...

  7. Unix传奇

    转自 http://coolshell.cn/articles/2322.html 了解过去,我们才能知其然,更知所以然.总结过去,我们才会知道我们明天该如何去规划,该如何去走.在时间的滚轮中,许许多 ...

  8. hibernate之helloword(环境搭建)

    环境搭建 hibernate.cfg.xml <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE ...

  9. c# json转换成dynamic对象,然后在dynamic对象中动态获取指定字符串列表中的值

    using Newtonsoft.Json;using System;using System.Collections.Generic;using System.Linq;using System.T ...

  10. Django URLs error: view must be a callable or a list/tuple in the case of include()

    Django 1.10 no longer allows you to specify views as a string (e.g. 'myapp.views.home') in your URL ...