• 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. React-Native 获取node.js提供的接口

    一个简单的React-Native 获取node.js提供的接口的实现 一.node.js var http = require("http"); var url = requir ...

  2. 【SQL语句】 - 在所有存储过程中查找关键字,关键字不区分大小写 [sp_findproc]

    USE [EShop]GO/****** Object: StoredProcedure [dbo].[sp_findproc] Script Date: 2015/8/19 11:05:24 *** ...

  3. JQ 事件

    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/ ...

  4. 在C#中使用CastleDynamicProxy 实现AOP

      原文链接:Aspect Oriented Programming (AOP) in C# using CastleDynamicProxy 本文主要展示在C#中如何使用Castle Dynamic ...

  5. AngularJS如何使用ngRepeat过滤排序

    NG重复指令,带过滤器,像这样: <li ng-repeat="item in items | orderBy:'order_prop' | filter:query | limitT ...

  6. 从苹果的appstore谈谈web前端那丝毫的追求

    献上链接:点击进入itunes打开页面,我们先找到App 的logo图比如这个图很简单的一个图标,估计多数人选择的是上传一张处理好圆角,border的图片作为app logo,但问题是苹果觉得,你们每 ...

  7. Wordpress主题中常用代码总结

    1. 在 Wordpress主题中显示最热文章的 PHP代码 <?php $result = $wpdb->get_results("SELECT comment_count,I ...

  8. 时间TDateTime相当于是Double，即双精度数64位，终于查到它用11位表示e，53位表示精度（整数小数一起），最前面一位表示正负

    http://docwiki.embarcadero.com/RADStudio/Seattle/en/Internal_Data_Formats 关于Double的RTL函数,好像就一个:TrySt ...

  9. c++ 17介绍

    作者:hearts zh链接:https://www.zhihu.com/question/32222337/answer/55238928来源:知乎著作权归作者所有.商业转载请联系作者获得授权,非商 ...

  10. cf452A Eevee

    A. Eevee time limit per test 1 second memory limit per test 256 megabytes input standard input outpu ...