• 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]C# 中的.pdb/ .vshost.exe/ .vshost.exe.manifest文件讨论

    原文出处:http://blog.163.com/chwei_sunshine/blog/static/19412628320125893656652/ pdb文件: 英文全称:Program Dat ...

  2. Java学习——继承

    将学生工人的共性描述提取出来,单独进行描述,只要让学生和工人与单独描述的这个类有关系,就可以了. 继承:1,提高了代码的复用性.2,让类与类之间产生了关系.有了这个关系,才有了多态的特性. 注意:千万 ...

  3. LINQ 操作符

    using System; using System.Collections.Generic; using System.Text; using System.Linq; namespace LinQ ...

  4. myeclipse内存不足有关问题

    myeclipse内存不足有关问题 myeclipse内存不足问题 使用myeclipse8.5出现如下问题:MyEclipse has detected that less than 5% of t ...

  5. php Debugging with Xdebug and Sublime Text 3(转)

    Debugging – we all do it a lot. Writing code perfectly the first time around is hard and only a few ...

  6. sqlite在c++中的使用方法

    1.需要下载的文件      http://pan.baidu.com/s/1c06NpzM 2.执行文件shell的编译 3.在c++中如何使用 #include <stdio.h> # ...

  7. Qt 五子棋

    http://blog.csdn.net/baiding1123/article/details/17194535

  8. .Net框架中，.ashx页面访问session

    public class ClassName : System.Web.SessionState.IRequiresSessionState 需实现session接口

  9. php-fpm日志告警"seem busy"

    php-fpm日志中出现"WARNING: [pool www] seems busy (you may need to increase pm.start_servers, or pm.m ...

  10. fdisk -l 找不到分区怎么办？想办法找到隐藏分区。

    centos6.6 装系统的时候,选取系统默认分区.装好后发现少了一大部分空间,通过fdisk -l 找不到分区,另外使用 parted -l 同样找不到消失的柱面. 如: [root@mysql]# ...