PRELOADER

Dinghow的个人博客

Home

2/16/2019 —— 

  • After a quick start of the Neural Network Intelligence (NNI) , I try using NNI in my own deep learning project. Recently, I’m buried in prostate cancer detection, one of its steps is to do image class

     2019-02-14 View all

    0. PrefaceThis is my first time to learn Automated machine learning(AutoML), I used to think the selection of model and the configuration of hyper-parameters must be settled manually, until I took par

     2019-02-13 View all

    3. 卷积神经网络灰度图使用灰度图的原因是避免颜色对分类造成影响 统计不变性(Statistical Invariants) 当两种输入可以获得同样的信息(如猫的位置与分类并没有关系),则应该共享权重,并利用这些输入来训练对应的同一权重 参数共享(Parameter Sharing) 应用参数共享可以大量减少参数数量,参数共享基于一个假设:如果图像中的一点(x1, y1)包含的特征很重要,那么它

     2018-12-16 View all

    因为之前已经有过Google那套ML的笔记,所以很多重复的部分就没有再写了,算是做了一些DL上的补充吧,其实严格意义上来说,Google那个课程应该算DL的入门课程,机器学习的很多非神经网络的算法:K-means、决策树这些都没有讲。Whatever,希望对你也有一些帮助~ 0. 杂记关于吸引盆(basin of attraction)多层神经网络的初始化隐层不能简单置0的原因,因为0很容易陷进一

     2018-11-28 View all

    1_notmnist is the first practice of Udacity Deep Learning course. The solution ipynb file is in my github repository In part 1, we used some methods to process the data, and in this part, we will tr

     2018-10-28 View all

    1_notmnist is the first practice of Udacity Deep Learning course. The solution ipynb file is in my github repository 1. Problem 1 Let’s take a peek at some of the data to make sure it looks sensible

     2018-10-27 View all

    系列笔记索引:官方课程 Github仓库 Part1:基础概念,降低损失 Part2:泛化,验证,表示法,特征组合 Part3:L2正则化,逻辑回归,分类 Part4:L1正则化,神经网络 Part5:训练神经网络,多类别神经网络,嵌套 14. 训练神经网络最常见的神经网络训练算法:反向传播算法(BP算法,BackPropagation) 是一种与最优化方法(如梯度下降法)结合使用的,用来训

     2018-09-24 View all