• cross entropy loss is not quite the same as optimizing classification accuracy. Althougth the two are correlated.
  • It's not necessarily true that Deep learning approaches are often said to require enormous amount of data to work well. In this competitation, there'are 30,000 examples for 121 classes.
    To achieve this, some tricks are :

    • dropout
    • weight decay
    • data argumentation
    • pre-training
    • pseudo-labeling
    • parameter sharing
  • The method is implemented based on Theano:
    • Python, Numpy, Theano, cuDNN, PyCUDA, Lasagne
    • scikit-image: pre-processing and data argumentation
    • ghalton: quasi-random number generation
  • Hardware:
    • GTX 980, GTX 680, Tesla K40
  • Pre-processing and data argumentation:
    • Normalization: pre-pixel zero mean unit variance

to be finished

"Classifying plankton with deep neural networks" notes的更多相关文章

  1. Classifying plankton with deep neural networks

    Classifying plankton with deep neural networks The National Data Science Bowl, a data science compet ...

  2. Training Deep Neural Networks

    http://handong1587.github.io/deep_learning/2015/10/09/training-dnn.html  //转载于 Training Deep Neural ...

  3. 课程一(Neural Networks and Deep Learning)，第四周（Deep Neural Networks） —— 3.Programming Assignments: Deep Neural Network - Application

    Deep Neural Network - Application Congratulations! Welcome to the fourth programming exercise of the ...

  4. Training (deep) Neural Networks Part: 1

    Training (deep) Neural Networks Part: 1 Nowadays training deep learning models have become extremely ...

  5. 为什么深度神经网络难以训练Why are deep neural networks hard to train?

    Imagine you're an engineer who has been asked to design a computer from scratch. One day you're work ...

  6. [C4] Andrew Ng - Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

    About this Course This course will teach you the "magic" of getting deep learning to work ...

  7. On Explainability of Deep Neural Networks

    On Explainability of Deep Neural Networks « Learning F# Functional Data Structures and Algorithms is ...

  8. Introduction to Deep Neural Networks

    Introduction to Deep Neural Networks Neural networks are a set of algorithms, modeled loosely after ...

  9. 深度神经网络入门教程Deep Neural Networks: A Getting Started Tutorial

    Deep Neural Networks are the more computationally powerful cousins to regular neural networks. Learn ...

随机推荐

  1. html标签之meta标签

    1  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />   ...

  2. mvc 笔记

    @{ ViewBag.Title = "主页"; } <div> 这里就是渲染Body啦.~~不需要写神马<asp:Content />,其实因为Rende ...

  3. js new Date()

    1.Date 对象用于处理日期和时间.创建 Date 对象的语法:var myDate=new Date()Date 对象会自动把当前日期和时间保存为其初始值.2.参数形式有以下5种: new Dat ...

  4. javascript 高级程序设计学习笔记（面向对象的程序设计)继承

    ECMAScript中描述了原型链的概念,原型链是实现继承的主要方法. 实现原型链继承有一种基本模式 function SuperType () { this.property = true; } S ...

  5. python时间函数

    import time print time.time() print time.localtime() fm = '%Y-%m-%d %H:%M:%S' YMD = time.strftime(fm ...

  6. wampserver 2.2装好后80端口未被占用,却打不开localhost

    在windows server 2003中装好wampserver2.2后打不开localhost,点击服务全部启动(颜色是橙色)也是打不开,我解决的原因是:安装mysql中sevice中的安装测试服 ...

  7. ZJUTACM（hd1259）

    ZJUTACM 点我 Time Limit: 2000/1000 MS (Java/Others)    Memory Limit: 65536/32768 K (Java/Others)Total ...

  8. centos 安装amp 运行环境+配置虚拟地址

    一.安装 MySQL 首先来进行 MySQL 的安装.打开超级终端,输入: [root@localhost ~]# yum install mysql mysql-server 安装完毕,让 MySQ ...

  9. thinkphp中的_get,_post,_request

    ThinkPHP没有改变原生的PHP系统变量获取方式,所以依然可以通过$_GET. $_POST.$_SERVER.$_REQUEST 等方式 来获取系统变量,不过系统的Action类提供了对系统变量 ...

  10. 【Leetcode】寻找数串中连续最大整数和且最大长度的子串

    寻找数串中连续最大整数和且最大长度的子串 输入示例: 1000 -100 200 -200 100 -100 10 90 输出结果: 1100 分析: 分治法解决问题非常方便,依然分为三种情况:a[1 ...