Break into AI

Hey there 👋🏼, so you are interested in entering in this field. You’ve come to the right place. Let me help you get started.

For starters, Who am I?
Well, the answer is I am you. Confused?
I am the same as you, only the difference is I am you skipped ahead in time.
I also was in the same place as you are now, a person who wants to enter into this field, but does not know where to start.
There is only one solution to this problem in all —
“‘There is not any one magic resource or way for you to start or learn it all’’
The point is to just start somewhere.

Some may ask:
‘If you are also showing us a way, Why are you writing this article?’
The point is just like I said there is not one holy grail to get into this field, best method is to try multiple ways and see what works best for you. Just like everyone has different tastes for food, everyone has their way of doing things.

Let’s consider for now that
‘This is the way’.

*Insert random Mandalorian meme with quote*

The Way

1. First and foremost you should be absolutely clear of the technical jargons that you keep hearing — Artificial Intelligence, Data Science, Deep Learning, Machine Learning.

As it is visible from the diagram, multiple of those terms are subsets of each other.

Artificial Intelligence — A set of methods which enables the machine to demonstrate machine intelligence. Eg. Knowledge Base
Input — If you have a car, you can go to the city. If you can go to the city, you can visit the fair.
Output — If you have a car, you can visit the fair.

Machine Learning — A subset of AI which contains various algorithms which use mathematical models to learn patterns in data and infer results on unseen data. Eg. Logistic Regression — An algorithm which learns to classify between two classes.
Input — Data of students with marks
Output — Did the student Pass/Fail

Deep Learning — A subset of Machine Learning which uses neural networks(A mathematical model inspired by how the brain works) to infer patterns from very large amounts of data.

Data Science — A field which employs these methods, domain knowledge, statistics to make sense out of unstructured data to achieve a final goal.

2. ’How much Mathematics do I need?’
You should be comfortable with basics of Linear Algebra and Calculus.
After that learn along the way, your answers are just a Google search away.
If you think you need to revisit, this channel is good place to start.

3. Let’s start with Machine Learning now.
We’ll be learning with The Andrew Ng.

He has a catchphrase —
‘Don’t worry about it if you don’t understand’.
Seriously, worrying is not going to help you figure out that the change in loss w.r.t filter is itself a convolution or know how converting a primal to a dual problem by Lagrangian method would help you compute the polynomial transformation without ever actually performing the transformation! I stressed on it so much because many a time, while learning you lose motivation to do so, seeing all the math.
But complex math is just simple math combined together and simple math is just simpler math clubbed together, just break it down, one piece at a time, Likewise!

Anyway If you’re interested in learning Deep Learning, you should be quite familiar with the groundwork which is laid down in Machine Learning. Given that Deep Learning is the most exciting field in ML, most problems can be solved using ML techniques like Random Forests and Ensemble Learning.
Deep Learning is great for complex tasks like Computer Vision, Natural Language Processing, etc.

Andrew Ng Machine Learning Course

• The fundamentals are explained quite amazingly. The Professor has broke down all the concepts to small bits so they are easy to grasp.
• The assignments in MATLAB are well tailored for each Week.

Some Gaps to Fill:

• I had quite a hard time understanding Support Vector Machines, PCA and the math behind it. Opencourseware videos like these are such a help.
• Backpropagation is explained way better in his Deep Learning course.
• Since the course is not in Python, you need to get familiar with the libraries, I have listed all the links at the end of the post.

Deep Learning Specialization

• Another masterpiece specialization by Andrew Ng and in Python
• Course mainly focuses on Neural Networks Part that you have learned in the earlier course, It is a set of five course focusing on NN, Vision and NLP.
• The courses touch on various research papers which have shaped Deep Learning to its Current State like YOLO, ResNet, Inception, etc.

Some Gaps to Fill:

• Tensorflow and the Keras API is not very well introduced.
• Course 5 Sequence Models(mainly LSTM) is not explained that well.

Some Advice to Fill the Gaps:

• It’s not about completing the courses for the certificates or just for the sake of. The assignments are small and you can complete them very fast if you just want to fill in the blanks. Take time to implement the algorithms in the first course using just Python from scratch, this will help you gain better intuition regarding the algorithm.
• Use the Coursera Discussion forums rigorously, they will answer all your questions.
• You may have trouble with understanding BackProp, for a normal NN it is easy. CNN, RNN, LSTM are troublesome. Do the calculus. It will help you in understanding what is happening behind the scenes.
• Get a book like the Hands-on ML book which covers both ML and DL.
  No, I am not affiliated with them in any way :). You will come across many algorithms which was not there in the first course such as Random Forests and even methods to evaluate your algorithm using various metrics.
  Very useful book if you aspire to be a ML Practitioner.

Last but not the least, Practise and Create. Don’t go on doing endless Courses.
And Remember always maintain this ratio : Consumption < Creation.

Visit our Repository for more Resources drafted by Domain Leads.

That’s all from my side Folks!

Thank you for reading

I like explaining things intuitively and answering “why” questions.
If you liked my article, do 👏🏼.
Your appreciation inspires me to ✍🏼write more.
Check out my other articles:

Bayes Rule and Sentiment Analysis

~Praful Mohanan
Connect with me on LinkedIn, Github.
If you need any help regarding ML, feel free to reach out!