Machine Learning in 30days.

Introduction

Hello everyone, my name is Duc. I'm CS student in HCM city Viet Nam. So this is first post. I'll try to write one post everyday.So let's get started.

Let's google!!!

Yes, Want to know something? Just google it. Well, let's see. When i google "machine learning" i have over 2 billions results.

That is a lot of information. A lot of courses, resource,etc. You can feel overwhelming. So do I. First we need declare clearly what is Machine Learning? Efficient way to learning ML? How to get a job with ML?. Actually, i don't know answer the quesion : how to get a job with ML? :D

What is Machine Learning?

• Wiki said :

Machine learning (ML) is the study of computer algorithms that improve automatically through experience.[1] It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so.[2] Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.

• Do you get that? if yes, you're better than me.
• With me, i will do not ask what is ML? first. Instead of that, i will ask why we need ML?. I found the answer on Caltech the main meaning answer is: we can't solve problem with normal algorithm, and the problem have pattern. What is pattern mean ? The partern mean is: the price of house increase follow: rooms, local,... Recognize dog in image, etc.

A litte things we need to know :

1. Python: absolutely, Python is the most common in ML. You shouldn't think Python is the best language for ML. Although, yes it is :D. The reason for Python is the most common in ML is easy to learn, simple syntax, a ton packages support for you. C/C++, Assembly still have performance better than Python. But you don't want headache with pointer in C/C++ or writing function in Assembly when we do ML, right?

2. Matlab : yes, it is. No more explaining.

3. Math : yes. If you hate math, i think you can think again about ML. Some subjects you need to know like: Linear Algebra, Matrix Calculus, Statistical.

Not only that, but you also have to learn more. But that was too much with the beginning

Apologies:

I am not very good at English. So, sometimes I may use wrong grammar and vocabulary. Hope you can understand the content and help me with suggestions on English and article content.

References:

1. https://work.caltech.edu/telecourse
2. https://sites.google.com/site/fsubiwiki/home/data-mining/machine-learning/history
3. https://machinelearningcoban.com/