Linear Regression Model Guide - theory part
Introduction
Recently, I review the machine learning course of Andrew ng in Coursera. Surprisingly, I can still learn a lot, so I decided to write some posts👍.
To talk about linear regression, we must first have a basic understanding of what is machine learning. What is machine learning? abstractly speaking, machine learning is learning a function: $$ f(input) = output $$ where $f$ refers to the specific machine learning model. Machine learning is a methodology for automatically mining the relationship between input and output. Sometimes we find it hard to define a specific algorithm to solve some problems, and this is where machine learning shines, we can let it learn and summarize some patterns from data and make predictions. This is also where it differs from traditional algorithms (binary search, recursive, etc.). One has to admit that machine learning is fascinating by definition, and it seems to provide a viable framework for solving all intractable problems. It just so happens that many real-life problems are so hard that solving them with traditional algorithms is impossible.