• 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. Hortonworks 用于做 Sentimental Analysis的Hiveddl.sql 文件

    The hiveddl.sql script has performed the following steps to refine the data: Converted the raw Twitt ...

  2. 仅当使用了列的列表 并且 identity_insert 为 on 时 才能在表 中为标识列指定显式值

    当 IDENTITY_INSERT 设置为 OFF 时,不能向表 'products' 中的标识列插入显式值.” 示例: 1.首先建立一个有标识列的表:CREATE TABLE products (i ...

  3. Composer的使用

    安装 curl -sS https://getcomposer.org/installer | php 你可以使用--install-dir选项将Composer安装到指定的目录,例如: curl - ...

  4. WinCe 如何使应用程序只开启一个

    方法一: namespace MyNameSpace{ static class Program { [DllImport("Toolhelp.dll")] public stat ...

  5. sublime 控制台输入解决方案

    下面的配置是通过konsole控制台自带的参数解决了sublime不能输入的问题,这种方式适合任何一种语言 { "cmd": ["konsole"," ...

  6. 发现中文版《C Primer Plus第五版》示例程序的一个错误

    错误的程序出现再第17章的499页ListItemCount()和500页的Traverse()两个函数上. 原著包含所有函数定义的list.c如下: #include<stdio.h> ...

  7. C语言学习笔记frist---输入两个数比较大小

    C#学习中,问道艰辛,今自C学起,第一个函数学习:输入两个数比较大小,仅作练习: #include "stdafx.h" #include<stdio.h> // 包含 ...

  8. python学习day9

    目录 一.队列 二.生产者消费者模型 三.协程 四.select\poll\epoll 五.paramiko 六.mysql API调用 一.队列(queue) 队列分以下三种: class queu ...

  9. rails跑通第一个demo

    rails -h 查看帮助 Usage: rails new APP_PATH [options] Options: -r, [--ruby=PATH] # Path to the Ruby bina ...

  10. linux之SQL语句简明教程---ALTER TABLE

    在表格被建立在资料库中后,我们常常会发现,这个表格的结构需要有所改变.常见的改变如下: 加一个栏位 删去一个栏位 改变栏位名称 改变栏位的资料种类 以上列出的改变并不是所有可能的改变.ALTER TA ...