• 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. 【转载】Xcode6中添加pch文件

    //原文地址:http://www.cnblogs.com/YouXianMing/p/3989155.html 1. 新建工程: 2. 创建pch文件:cmd+n->other->PCH ...

  2. oracle函数trunc的使用

    1.日期比较时精确到日,可以使用 TRUNC(sysdate,'dd')函数.函数支持格式有:yyyy MM  dd  hh Mi可以用   select TRUNC(sysdate,'yyyy') ...

  3. CodeForces 222D - Olympiad

    第一行给出两个个数字k和n,第二三行分别有k个数字,求将第二.三行之间的数字相互组合,求最多有多少个组合的和不小于n 纯粹暴力 #include <iostream> #include & ...

  4. word保存时标题变成黑框（mac版本）

    参考:http://blog.sina.com.cn/s/blog_686020310101i2zu.html 参考文档中说的时windows版本的word,跟我mac处理方式有一些不同: word版 ...

  5. 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 ...

  6. jQuery插件的点点滴滴

    说起jQuery插件,很多人的脑海种已经有了一定的雏形,仿佛感觉仅仅就是那样子,事实呢?当你看了Bootstrap.js,品读了slidesjs,观摩了jquery.cycle2.js,不禁发现,原来 ...

  7. Javascript-数据类型、类型转换

    typeof 判断数据类型: var n = 1; var t = "echo"; var fn = function() {} var arr = [1,2,3]; typeof ...

  8. LinearLayout遇到的问题——利用LinearLayout做横向滑动冲突

    问题:当我添加两个TextView的时候,然后滑动,发现只生成了一个TextView. 就是 <?xml version="1.0" encoding="utf-8 ...

  9. *1022. D进制的A+B【考前最后一道题】

      /* *Main.c *1022. D进制的A+B Ver.1 *Created on : 2014.9.5 *****测试通过****** */ #include <stdio.h> ...

  10. android Xml生成一条细线，以及获取屏幕宽度和高度

    <View android:layout_width="match_parent" android:layout_height="2dip" androi ...