• 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. HDU 5791 Two

    题意:给两个序列,求公共序列的个数 分析:很自然想到最长公共子序列的转移的转移形式,用dp[i][j]表示第一个串前i个 和第二个串前j个匹配的答案数量,a[i]==b[i],dp[i][j]=dp[ ...

  3. 在linq查询环境下通过sql语句来访问数据库

    接上一篇随笔 这里主要介绍在linq环境下,如果实现用sql来访问数据库,同时也介绍在EF框架中如何添加新的方法来访问数据库. 1.首先,在数据访问层(EF.DAO,EF.IDAO)中添加具体的函数来 ...

  4. Python－windows服务－重启自动化

    一. 前言 有了上一篇的“python初学”的基础,咱们就有了python的开发包,有了开发环境IDE,那我们就可以干活了.我的第一个选题就是让我们的windows服务可以按照我们的意愿进行自动重启. ...

  5. 班上有学生若干名，已知每名学生的成绩（整数），求班上所有学生的平均成绩，保留到小数点后两位。同时输出该平均成绩整数部分四舍五入后的数值。 第一行有一个整数n（1<= n <= 100），表示学生的人数。其后n行每行有1个整数，表示每个学生的成绩，取值在int范围内。

    #include<iostream> #include<iomanip> using namespace std ; int main() { int n; while(cin ...

  6. Fragment之一：基本原理

    1.低版本API对Fragment的支持 Fragment必须被加载进Acitivity中,才能呈现.而在低于3.0版本的API中,由于不存在Fragment,因此必须使用support包: (1)对 ...

  7. flask 后台表单验证模块

    我不想直接用flask的wtf模块,太大,功能太多,用不了.但后台也不能不做验证吧,我比较懒,不想一行一行写代码验证,所以就写了一个验证模块,对于小项目也够用了 # encoding=utf-8 # ...

  8. humble number(hd1058)

    Problem Description A number whose only prime factors are 2,3,5 or 7 is called a humble number. The ...

  9. Asp.net MVC 之 ActionResult

    Action运行完后,回传的值通过ActionResult 类别或者其衍生的类别操作.ActionResult是一个抽象类,因此,Asp.net MVC 本身就实作了许多不同类型的ActionResu ...

  10. JavaScript学习笔记：数组reduce()和reduceRight()方法

    很多时候需要累加数组项的得到一个值(比如说求和).如果你碰到一个类似的问题,你想到的方法是什么呢?会不会和我一样,想到的就是使用for或while循环,对数组进行迭代,依次将他们的值加起来.比如: v ...