Exploring Machine Learning: The beginning

Machine learning is not new and maybe has been overhyped but it’s an area that I’ve been interested in for awhile now. For me, the end goal is to learn how to use/create technology that enables human beings to do more meaningful work.

After being relieved of reading for Accounting professional (ACCA) exams about a week ago I finally had time to delve into it. It only made sense to try to learn what I was really interested in at the moment.

Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed.

Here are a few widely publicized examples of machine learning applications you may be familiar with:

• The heavily hyped, self-driving Google car? The essence of machine learning.
• Online recommendation offers such as those from Amazon and Netflix? Machine learning applications for everyday life.
• Knowing what customers are saying about you on Twitter? Machine learning combined with linguistic rule creation.
• Fraud detection? One of the more obvious, important uses in our world today.

My plan was simple, do 3 things.

Learn Python

It’s an easy to understand programming language and relevant for Machine learning. I started on codecademy just to get an overview, I also got an ebook just in case internet connection fails me, I’d still be able to go through the basic curriculum. So far it’s been quite friendly, and a knowledge of the basics has been quite helpful in relating with the syntax on Octave.

 Take a Tutorial online 

For the sake of structured learning, I was either going to take a YouTube Tutorial or a MOOC. I found a good one on YouTube but for starters, I decided to go with taking the quite popular Machine Learning Course on Coursera by Stanford University after reading a couple of reviews. I had to download the first 5 weeks overnight just so I’m not bothered about internet issues. So far all I’ve been doing is maths related stuff — Linear Regression and Matrices, watching videos in transit and checking up the meaning/explanation of various terms. I haven’t gotten to the fun part where I can see the correlation between what I’m doing and real-life application but it’s only necessary I pass through this stage. I don’t fully understand what I’ve learned so far but when learning something new it’s only normal that the learning curve is steep.

For practicals we’re either to use Matlab or Octave, I initially wanted to go for Matlab because it’s user interface looked more appealing but there’s some error showing up anytime I try to download the additional resources needed to run the program. So I would download octave later in the middle of the night as I’ve had two failed attempts due to it’s file size and internet speed.

Work on a real project then decide if its worth my while

This part was supposed to be done later after I’ve was done with the online course but I recently signified interest to join a group of coursemates who also want to work on real projects, things haven’t kicked off yet, when it does I would follow the conversations and contribute anywhere I can. It’s pretty much a diverse a group of people from different countries with more experience than I do so I’m hoping to learn and connect.

For the next one year I would be learning as much as I can by the side, I would always keep my learning style simple.

Maybe I’d end up falling in love with this or maybe not, it would definitely help in learning how to use/create technology to enable human beings to do more meaningful work.

I’m open to any advice or help from anyone experienced or knowledgeable AI/ML.

I would be back to give an update on my progress.

 

Update on 5/7/2020: I learnt ML for about 9 months, did a few projects esp in sentiment analysis. It was a good experience, while I won’t be taking up ML full time, what I learnt has been helpful as look to implement it in my day to day Job.

One more thing: 

Are you looking to learn about ML?

FutureLearn helps learners discover the ability of artificial intelligence to transform their everyday life and reshape the way they work