Stanford University free online Machine Learning course

As an instructional designer and technical instructor I have a vested interest in robust, effective online learning environments. Recently, I completed free Stanford online class Machine Learning taught by Dr. Andrew Ng. Several elements made this course multiple week course an very engaging learning experience. The lectures are generally short. Dr. Andrew Ng introduces each lectures talking informally to the camera. We watch him turn to the laptop behind him and the lecture flows seamlessly into voice over slides with annotation. Dr. Andrew Ng has a real knack for presenting just the right amount of mathematics at the heart of an algorithm. He strives to impact an intuitive grasp. As he lectures Dr. Ng annotates the slides freely with reinforces the informal setting.

Another effective element are the brief self-test quizzes. These one slide multiple choice quizzes occur several times during a lecture and can really snap you into back into focus. They are optional.

The course schedule is well structured with weekly assignments to watch one or more lectures, complete a multiple choice review test, and complete the programming exercise. You are encouraged to retake the review test until you get all the answers right. All review question appear to be randomly drawn from a large pool of questions, with possible answers scrambled.
Some review question appear to be algorithmically generated.

The programming exercises use Octave, which is a free, open-source version of MATLAB. The typical programming exercise calls for completing a small number of Octave functions which fit neatly into some incredible applications. The course provided a submission script for each solution as you work thru the programming exercise. Behind the scenes, some infrastructure automatically tested the solutions and accumulates your score accordingly.

Yet another component is the Q&A Forum which allows to you follow posts of interest.

I used Evernote to screen capture the slides at key moments and to document my programming exercises.

At the end of the course, I received a Statement of Accomplishment.

December 31, 2011 

Dear Jan Alden Cornish (janaldencornish@gmail.com),

Congratulations! You have successfully completed the online Machine Learning course (ml-class.org), offered October through December, 2011. To successfully complete this online course, students were required to watch lectures, complete review questions, and work through programming exercises. Your score on these components were as follows:

• Review Questions: 80 out of a maximum of 80 
• Programming Exercises: 800 out of a maximum of 800

Exploring Data Visualizations with Tableau Public

Powered by Tableau

Evaluating Kindle reader for the MacBook and a Window XP Netbook

I have to say there's some promise here with the Kindle reader for the MacBook and also for a Window XP machine, but I am disappointed with them for reading technical material. I am reading a book on business analytics for the Web Analytics Book Club. We meet weekly to discuss the current chapter. The eBook has no page numbers which makes it impossible to quickly let people know what "page" I am referring to. We are using an audio conference call, not a web conference, so there's no screen sharing. The book itself has very minimal section numbering. Also, I am reading the same book on both platforms, one platform in my office and one platform in our den. This caused the reader for the MacBook to crash repeatedly.

Scheme Lives on in the R Language

Today I made an interesting discovery while continuing to work my way thru "R in a Nutshell" by Joseph Adler. R is an open source interactive language, very widely for statistical analytics and data mining. R is derived from S, one of several statistical computing languages from Bell Laboratories. The more I read, the more R strongly reminded me of Scheme, a modern dialect of Lisp. I wasn't totally surprised when I did a Google search and found

The initial authors of R said¹, "...we implemented the language by
first writing an interpreter for a Scheme subset and then
progressively mutating it to resemble S."

Grading My Blog

I've discovered Hubspot's Blog Grader. But I noticed a statement in the generated report that that's clearly false. The blog janaldencornish.blogspot.com is estimated to have approximately 49,059,023 unique visitors last month.

Learning Web Analytics through Helping Non-Profit Organizations

Founded in 2010 by the Web Analytics Demystified partners, The Analysis Exchange is the world's only educational network connecting nonprofit and nongovernmental organizations with motivated individuals trying to get hands-on experience doing web analytics. Open to all regardless of geography, association, or ability to pay, the Analysis Exchange has been described as a profound innovation in the digital measurement sector.

View my Analysis Exchange profile which summarizes my completed projects.

Searching for a Problem Resolution

Recently I chatted with Yahoo Support to resolve an issue with Search. This is a third time I have had this problem. Can you propose a theory why Yahoo doesn't document this issue?

Natalie: As you've mentioned, your mail search feature is not pulling up all possible results. Is that correct?

Jan Alden Cornish: yes, you said it well. THis has happened before and twice it was resolved by some undisclosed magic your team has in its arsenal of tricks

Natalie: Thanks for bringing this matter to our attention and I apologize for the inconvenience that this has caused you.

Natalie: May I have the permission to access your account?

Jan Alden Cornish: yes, you have my permission

...

Natalie: Thank you.

Natalie: Sign out of your Yahoo! Mail account completely. Just tell me when you're out, okay?

Jan Alden Cornish: On both my machines?

Natalie: Please be sure that you will sign out to all your Yahoo! Mail account.

Jan Alden Cornish: Ok

Jan Alden Cornish: I spoke too soon. Now I am out

Natalie: Please provide us with the following information:

Natalie: 1. The key word you are using to search.

Jan Alden Cornish: Pardee

Natalie: 2. The location of the email. (Inbox, Trash, or other folders)

Jan Alden Cornish: Inbox

Natalie: 3. The number of search results you are expecting (estimate).

Jan Alden Cornish: probably around 15 but I have one exact email that was not returned that should be been in the search results

Natalie: 4. Number of search results you actually received.

Jan Alden Cornish: Now if I just exited all my email sessions, I can't answer that.

Natalie: Please hold for 2-3 minutes while I access your account and check it out for you.

Jan Alden Cornish: Please understand I have one email I know for sure should have been returned

Natalie: Yes, I understand.

Jan Alden Cornish: ok

Natalie: Thanks for waiting. I'm now done accessing your account and I was able to duplicate your issue.

Natalie: Please hold for 3-5 minutes while I try to troubleshoot your account.

Jan Alden Cornish: wow. Without my telling you the specifics of the email?

Natalie: I checked for the most recent mail.

Jan Alden Cornish: Yes, I found the email by searching on my Blackberry, and then locating it in my Yahoo inbox and then replying to it.

Natalie: Alright.

Jan Alden Cornish: ok

Jan Alden Cornish: these problems are preventing me from being as productive as I can.

Natalie: My apologies for the inconvenience.

Jan Alden Cornish: Thank you, I appreciate your empathy

Natalie: Thanks for waiting. I'm now done with the necessary troubleshooting steps.

...

Jan Alden Cornish: What is the root cause? Is it related to the size of my Inbox?

Natalie: No, Jan.

Natalie: Your mail account just needed to be refreshed.

Natalie: Thanks for your patience and understanding.

Jan Alden Cornish: Is there a user-level command in Yahoo Mail whereby I can execute the "refresh"

Natalie: Unfortunately, the refresh should be done at our end.

Natalie: Please tell me if you'll still encounter the same issue.

Jan Alden Cornish: The problem that I was experiencing was resolved.

Natalie: That's good to hear.

Natalie: For the meantime, could I help you with anything else?

Jan Alden Cornish: How often will this refresh need to be run>

Natalie: There is no exact time limit.

Natalie: Will there be anything else?

Jan Alden Cornish: Do I need to experience a problem with Search before requesting a refresh?

Natalie: Yes, Jan.

Jan Alden Cornish: Is a support document that provides a problem description?

Natalie: No, Jan.

Jan Alden Cornish: Ok, well, as long as your team is available to help with running this command...

Natalie: We are available 24 hours a day and 7 days a week.

Natalie: Could I help you with anything else before you go?

Jan Alden Cornish: Would decreasing the size of my Inbox reduce the chance of this problem happening again?

Natalie: The size of your Inbox should not be the cause of this issue.

Jan Alden Cornish: That's good to know

Jan Alden Cornish: Thanks for your help.