Blog Archives

A VGG-like CNN in keras for Fashion-MNIST with 94% accuracy

September 7, 2017
By
A VGG-like CNN in keras for Fashion-MNIST with 94% accuracy

In many introductory to image recognition tasks, the famous MNIST data set is typically used. However, there are some issues with this data:1. It is too easy. For example, a simple MLP model can achieve 99% accuracy, and a 2-layer CNN can achieve 99% a...

Read more »

A VGG-like CNN in keras for Fashion-MNIST with 94% accuracy

September 7, 2017
By
A VGG-like CNN in keras for Fashion-MNIST with 94% accuracy

In many introductory to image recognition tasks, the famous MNIST data set is typically used. However, there are some issues with this data:1. It is too easy. For example, a simple MLP model can achieve 99% accuracy, and a 2-layer CNN can achieve 99% a...

Read more »

如何零基础使用KERAS搭建实用深度模型

September 3, 2017
By
如何零基础使用KERAS搭建实用深度模型

在这篇小文章中,我们将简要讨论如何使用KERAS这个现在最新的深度学习框架来构造实用的深度学习模型。 深度学习是目前最热门的高级分析技术之一,在很多方面表现出了超越传统机器

Read more »

如何零基础使用KERAS搭建实用深度模型

September 3, 2017
By
如何零基础使用KERAS搭建实用深度模型

在这篇小文章中,我们将简要讨论如何使用KERAS这个现在最新的深度学习框架来构造实用的深度学习模型。 深度学习是目前最热门的高级分析技术之一,在很多方面表现出了超越传统机器

Read more »

CNTK integrated into Keras

June 13, 2017
By
CNTK integrated into Keras

Keras is a very convenient tool to build your deep learning model from scratch, it is so easy to use that it almost becomes the de-facto deep learning modeling framework in Kaggle competition.Keras used to support only TensorFlow and Theano.  CNTK...

Read more »

Google’s switch to G Suite

February 20, 2017
By
Google’s switch to G Suite

My paymenet information for this custom URL is expiring and Google told me to update the payment information. That's OK, I will do it. However, by switching to G Suite, Google makes paying this $10.00 so difficult that I decided it is not worthy to c...

Read more »

Install Theano under Anaconda3 Python 3.5

August 11, 2016
By
Install Theano under Anaconda3 Python 3.5

Update on 2017/01/05:With the release of Anaconda3-4.2.0 in September 2016, users are able to install mingw and libpython under conda, which makes  using Theano and keras in Python3.5 much easier.Here are the simple steps:1. Install Anaconda3-4.2....

Read more »

Add Table of Contents to your Jupyter Notebook

August 10, 2016
By
Add Table of Contents to your Jupyter Notebook

Jupyter notebook does not support Table Of Contents (ToC) out of box, unlike R Markdown. There are nbextensions that ppl made to support this. It is easy to add this capability, following these steps to add Table of Contents to your notebook: 1. F...

Read more »

Fast SQL moving average calculation without windowing functions

May 11, 2015
By
Fast SQL moving average calculation without windowing functions

In this post, I show a trick to do moving average calculation (can be extended to other operations requiring windowing functions) that is super fast. Often, SAS analysts need to conduct moving average calculation and there are several options by the or...

Read more »

sklearn DecisionTree plot example needs pydotplus

April 26, 2015
By

In Python, sklearn (scikit-learn)'s DecisionTree example uses pydot for plotting the generated tree: @here.But for Python 3, pydot has some issues with the string from dot_data.getvalue(), for example it will report "TypeError: startswith first arg mus...

Read more »


Subscribe

Email:

  Subscribe