Intro Post

Hi everyone!

Why are you reading my blog? What's wrong with you????

Just kidding. But seriously, I have no interest in seeking new viewers, mostly because this blog is going to act like a journal to me. I will use it to note my progress as I learn, and also occasionally make inappropriate and unfair rants.

Why make this public to the internet? Because:

• I am kind of interested in hearing what other people have to say, so if someone comments and says hello, they are totally welcome to do so. It's just not a priority to seek that out right now.
• This way I have all my notes easily available to me with the power of the internet.
• I'll be able to show off! But first I have to friggen learn... :'(

That's sort of it. So yeah. You can watch me flounder in ML and ramble away. I don't have much more to add. I've already started an annotated bibliography of everywhere I read. I'll probably leave stuff out because oops, and also because I don't have a huge amount of excess energy to expend on the effort to express every experience I... I don't have another e-word for this stupid sentence. Please forgive me for writing it.

Love ya!

<3 <3

Devin's Reference Guide: Articles, Posts, and Books I Found Useful

Hi everyone! I'm new to Machine Learning right now, so this post is going to be my bibliography. I will annotate it with my thoughts as I learn, and I hope to update it as I go along.

Things I've read so far!!!!

• http://archive.ics.uci.edu/ml/
• This is a really cool site, with real-world data I can use to test the algorithms I plan to write! I'll see how it goes. Some sets are incomplete, so if you're not ready for that (I'm not), keep that in mind and be sure to check (it says on the page before you download).
• Learning scikit-learn: machine learning in Python, a book I can read through my local library (it's an e-book so I can read on the web, woo!). Authors are Raúl Garreta, Guillermo Moncecchi, and the book was published 2013.
• So far I don't like the book because there are typos in the code snippets and also it doesn't always have the import statements for some things (like it neglected to say "import numpy as np" and then there was another object that I couldn't figure out, called sca, probably some sort of scalar thing?). But it looks like if you download the actual source code on the internet (dunno if I can do that, I'll check later, and it might cost money) then you might not have to worry about that. Anyway, this isn't really the kind of book I'm looking for, as I want to learn the algorithms by writing them myself, and so far it doesn't look like that happens.
• http://machinelearningmastery.com/a-tour-of-machine-learning-algorithms/
• This website has a categorized list of algorithms. I plan on using the list to research and study new topics as I go. So far the author and blog looks cool, so I will be back later.
• http://setosa.io/ev/ordinary-least-squares-regression/
• This site looks like it'll be helpful to learn Ordinary Least Squares Regression, the first algorithm I'm going to tackle. Woo!
• It's great because you can interact with the graphs. If you take all the points and make them vertical you make it have a NaN error and the graph is broken. Yay! Fun!
• Building Machine Learning Systems with Python - Second Edition by Willi Richert and Luis Pedro Coelho, whoever they are.
•  I like this book so far! Great stuff. I hope to get through a few more chapters over the weekend while I learn OLSR. I have too many things I want to learn... I'll learn them though! Go teamwork!
• OK I'm not liking this book so much anymore. It's a lot like the Learning scikit-learn book. What's similar? It's a bunch of code snippets showing you how to use scikit-learn, numpy, and scipy. But I want to learn more about the algorithms themselves! So, I think this book isn't quite for me. Both these books are good books on how to use machine learning algorithms, but I want to learn the algorithms. So. Moving on.
• https://www.coursera.org/learn/machine-learning
• This is a cousera free MOOC.
• I did some of the things before, then stopped due to mostly myself. So! I'm starting over and trying again. I believe in myself. 
• The guy (Andrew Ng) has a nice voice. 
• It's very informative and we'll learn about the actual algorithms. Yayyyyy!
• So far this has been great! I've actually learned how algorithms work. We've done linear regression so far, awesome, I've programmed gradient descent and the normalization method in octave so far. I'm going to convert it to python soon. Maybe also C++ because I want to become a better C++ programmer too. We'll see.

That's sort of it for now. I'll add more as I go!!