Beginning with Machine Learning - Part 1

Apoorva Dave on February 13, 2019

This question pops into almost everyone’s head who so ever wants to play with this new technology. I myself wondered as to from where should I be... [Read Full]
markdown guide

Thanks Apoorva Dave.
I'm a full stack web dev and i wants you help. Please help me.
I want to learn machine learning how to start i'm not good in math even i have not learn calculus and Linear algebra to get started and how much i should learn about math to get start with machine learning and become a master


So there are two cases - 1. if one has little knowledge of maths, he/she can start with ML concepts and while understanding the algorithm, they can improve maths skills as well. To code, maths might not be needed. But it is always advisable to understand the math behind the algorithm. 2. if one has no prior knowledge of maths, then my suggestion would be to first go through basic maths atleast and then start with ML. Learning maths will not just help you in ML but in other fields of computer science as well.


You can check the series "Beginning with Machine Learning" :) I am planning to write a new article in this series. Do let me know if any of you have anything in mind :) I will write on it if I could!


Well, I am very beginner on ML theme, but I will certainly let you know if something (idea or doubt) come up! thank you!


nice post.
please continue it with some practical examples


Sure will do. The next two posts will mainly focus on classification and regression concepts after which will give practical examples as well.


Nice πŸ‘Œ post
Can you please tell me where does Deep Learning fits into the above 3 categories of machine learning ?


You can say Deep learning is the next evolution of machine learning – it’s how machines can make their own accurate decisions without a programmer telling them so.
The types which I have explained in the post are different learning methods which we can use depending on our requirement. If the data is labelled then supervised else unsupervised.

A deep learning model is able to learn through its own method of computing – its own β€œbrain". And for this it uses a layered structure of algorithms called an artificial neural network (ANN).


Ohhh 😲🀀🀀
Well i guess Deep Learning is lit afπŸ”₯πŸ”₯
Looking forward for your new posts πŸ˜€


Deep learning refers to neural networks that are much deeper than the three to four layers people were using before. It's interesting because, in order to make it practical at all, you have to use a pretraining step which involves pretending that it's a totally different thing called a restricted Boltzmann machine. That pretraining, if you're lucky, acts as a form of feature extraction and can save feature engineering time.

The initial successes seemed almost magical and everyone leapt on it. It turned out that those successes were very specialized and, while it's a really useful tool, it's not the panacea people thought it might be.


Spectacular series, Apoorva! How do I get in touch if I have an idea to run by you about it? :)


There are numerous article on Machine learning but your article gave me good insights. Looking forward to more such article.


Thanks a lot! If you are interested in understanding some other concepts of ML like classification and regression as well then you can check my other posts in this series 😊

code of conduct - report abuse