It has been two weeks since I have started my Personal PhD. It is still very exciting! So far I am progressing along as planned for my first quarter curriculum.
Q1 curriculum:
Computer Science track:
1. I have finished Week 1 of Andrew Ng Coursera course right on my half-speed schedule of one week of course material in two weeks.
2. Watched 2 lectures of Automatic Speech Recognition class. It is very dense. Turns out Speech Recognition is based on Finite Automata. When I studied about Finite Automata in college I never thought that theory would be ever so useful. But here I am now using them at work. 🙂 Looks like there is a Coursera course specifically on Automata here.
Linguistics track:
3. I also started reviewing German a little bit every day as I will be going to Germany for vacation in August. Even if it is 10-30 minutes a day it all adds up!
4. Reading. I have started reading papers. So far the system for reading papers and keeping track of them is essentially non-existent: print out the paper, read it and mark it with pen, put it in a manila envelope with the rest of them. Next up I will try to track them in a Google spreadsheet with noting title, main idea in few sentences, concepts I need to learn about and any references I should follow up with. I have heard of Mendeley software developed for this purpose so will try it as well at some point later. If you have any suggestions, please let me know!
5. Writing. This update is coming two weeks after I started. So far so good 🙂
Learning Machine Learning
The introduction of Machine Learning talks about classification and linear regression. That looked very familiar. I am sure I have seen that stuff when I was doing Bioinformatics in college. Turns out there is quite a bit of overlap between Statistics and Machine Learning. Here [1] is one great Quora answer on what is difference between Statistics and Machine Learning:
“
- Machine Learning is AI people doing data analysis.
- Data Mining is database people doing data analysis.
- Applied Statistics is statisticians doing data analysis (mathematical statistics is mathematicians doing statistics, a meta-activity analogous to theoretical computer scientists investigating, say, PAC and convergence – which sometimes gets put into machine learning).
- Infographics is Graphic Designers doing data analysis.
- Data Journalism is Journalists
doing data analysis. - Econometrics is Economists
doing data analysis (and here you can win aNobel Prize). - Psychometrics is Psychologists
doing data analysis. - Chemometrics and Cheminformati
cs are Chemists doing data analysis. - Bioinformatics is Biologists
doing data analysis.”
I fit some of those terms into Google Trends and its interesting to see that Data Mining and Bioinformatics is loosing its popularity since 2005 and Machine Learning is searched more for since 2011 and passed Bioinformatics in popularity in 2013. Link [2]
Machine Learning is everywhere! Here [3] is an article about using Maching Learning to curb harassment in online game League of Legends.
I also discovered this blog about machine learning http://machinelearningmastery.
—