Sal Kahn on Mastery Based Learning

Sal speaks at TED about mastery-based learning

Would you choose to build a house on top of an unfinished foundation? Of course not. Why, then, do we rush students through education when they haven't always grasped the basics? Yes, it's complicated, but Sal shares his plan to turn struggling students into scholars by helping them master concepts at their own pace.  Created by Sal Khan.  ... " 

Python Deep Learning with Keras

Technical.  From Machine learning mastery, an introduction to using the Keras deep learning library for Python.

Value of Quick Descriptive Statistics

Just received from Jason Brownlee:

" ... Hi, you can learn a lot about your dataset by reviewing some basic descriptive statistics. ... The R platform provides a seemingly unlimited array of functions for poking and prodding your dataset in order to learn just that little bit more.   .. " 

My View:  I  am a big proponent of scanning data in this way.  It addresses both correctness and basic descriptive measures.  It also lets you quickly add some basic visualization to the data, which further lets you look for more subtlety in patterns.  Also,  I note that this does not need to be done in R, it can be done in Excel, Tableau, Spotfire, SPSS or many other methods.    I have had experience with descriptive methods saving me a large amount of later, more complex efforts.  Do try it. ...

Jason Brownlee sends along a note on now to do a simple descriptive review of data in R.  List below.    Jason summarizes:  " .. Below is my list of the 8 descriptive statistics I recommend you look at when reviewing your dataset in R:

1. Peek at the first few rows of your data
2 .Review the number of rows and columns you ave.
3. Review the data types of each column
4. Take a look at the class distribution (for classification problems)
5. Calculate a simple 5-number summary for each column
6. Review the standard deviations for each numerical column
7. Check the skewness of each column, handy to see what transforms to apply
8. Review the correlations between attributes

Learn the exact snippet of code to use for each statistic in the blog post:
  http://machinelearningmastery.com/descriptive-statistics-examples-with-r/

Nicely done, for more writing by Jason, see:   http://machinelearningmastery.com/author/jasonb/

And see his E book on the subject

Will report on the book in September.

Python Deep Learning Library

A Python deep learning library from Machine Learnining Mastery.    Technical, for the coder:

" ... Theano is an open source project released under the BSD license and was developed by the LISA (now MILA) group at the University of Montreal, Quebec, Canada (home of Yoshua Bengio). It is named after a Greek mathematician.

At it’s heart Theano is a compiler for mathematical expressions in Python. It knows how to take your structures and turn them into very efficient code that uses NumPy, efficient native libraries like BLAS and native code (C++) to run as fast as possible on CPUs or GPUs. .... " 

Evaluating Machine Learning Algorithms in R

Part of the problem with open source methods, like those in R, is that there are too many options.   How do you know which to use?  For research, for production?  Machine Learning Mastery provides some good thoughts on how to evaluate options.  With examples.

Machine Learning Mastery

Jason B has a blog on machine learning.  Good introductory piece: Why Machine Learning Matters.

Free Data Analytics Handbook

Looked at in Machine Learning Mastery.  " ... What is the difference between a Data Analyst and a Data Scientist and what type of work do they do all day?

These questions and questions like them are answered in the new free ebook The Data Analytics Handbook: Data Analysts and Data Scientists.

The ebook was created by Brian Liou, Tristan Tao and Elizabeth Lin. Brian and Tristan are Computer Science + Statistics grads and run the blog statsguys. Although they have jobs, they have taken the initiative to interview data analysts and data scientists in industry and ask questions around their background, how they were hired and daily routine. .... " 

Update: Have taken a look at the two volumes of this.  It is less a handbook than it is a group of interviews with young practitioners.  Not a How to.   Informative view of the current state of the business.  They will be updating it.  See more at related sites www.teamleada.com and statsguys.wordpress.com

Running a Simple Classifier

Been following Machine Learning Mastery, by Jason Brownlee.   He posted an item about a free classifier in Weka that I had not seen before.   He includes a step by step approach that is worth a look  Getting more tools to the people is a good idea.  In some cases they can use the tools themselves,  in other cases t can give an enterprising decision maker an understanding of what is required to make such a classifier useful.   Some like delving into the quantitative details.  Thanks Jason.

Machine Learning Mastery

I was just reminded of the blog Machine Learning Mastery, which gives technical but non mathematical advice about machine learning.   Most recently an item about improving learning results by getting information from multiple techniques.  This is a not uncommon strategy in analytics in general.   Check out the author: Jason Brownlee's site, where he provides more information, his motivations and goals.  I intend to follow more closely now.