Supervised, Unsupervised, Octave

These are the things I’ve come across today watching the course from coursera.

Supervised learning requires some sort of user input for the algorithm to work. The algorithm needs to be provided with the correct answers to come up with the results. This kind of learning uses regression. Unsupervised learning on the other hand does not need any inputs and will work on whatever data is provided. Clustering is used in this learning algorithm.

To prototype learning algos, a programming tool called Octave was recommended by the lecturer. Compared to other programming languages such as python or c++, this makes you focus purely on learning algorithms and not the technical jabbers of complex programming languages.

Will have to take a look at this language and have my self a go.


The Start

“A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.” — Tom Mitchell, Carnegie Mellon University

A quick google search and this is the quote that I got for machine learning.

So what is machine learning and why do I want to venture in this subject matter?

Machine learning varies in a number of applications, be it for improving safety, increasing sales, and a lot more. It consumes data from executed tasks which equates to an “experience”. Parameters are adjusted based from this experience and you’ll get whatever performance output you want.

Why do I want to study this subject matter?

First of  all, this is a hot in 2018 so it can be lucrative and could be the break in my career.

Another reason is I’m getting bored.

Let’s see how far I can go.