Where do you start if you want to learn Artificial Intelligence as a beginner?

As a beginner, we tend to have majorly skewed, if not the wrong ideas about what Artificial Intelligence really encompasses.

You have to understand, the entire hype surrounding AI is strongly built around fancy media lines, marketing campaigns and fairy tales.

Artificial Intelligence today is a class of self-learning, self-adapting and self-improving algorithms whose results rely almost entirely on the quality of data. Nothing is inherently “intelligent” about our algorithms, just really clever mathematics.

But on the brighter side, it holds promise to be the greatest technological advancement of our age. Many of us, like me, have faith in that promise. And since you are here, you must too.

Well to start with, I’d say you go with Machine Learning first. The reason is simple and twofold. One, besides being the best point of entry into AI, there are just a lot of resources out there to help you out and second, it is, for the most part, the least mathematically rigorous.

Before you begin, I do recommend you go through these very important prerequisites first:

• Linear Algebra and Matrix Multiplications: Chances are, almost any online course you take up, is going to be assuming that you’re 100% clear on matrix multiplications. And they might be easier to follow in the beginning, those do tend to get a little difficult to follow as you head to Artificial Neural Networks. Also, the knowledge of matrix multiplications allows you to do seriously cut down on your AI program runtime by substituting loops with vectorisation. If you want to pursue ML and be successful at it, your algorithms need to scale and for that vectorisation is absolutely critical for you to know and follow.
• Python: There has to be a reason somewhere if all the major players are drifting to Python for every programming need. Besides it being the most intuitive and beginner-friendly language I’ve ever seen, almost any course you take on Machine Learning is sure to be taught in Python. It’s a great language for learning purposes. Play around with Python’s libraries like NumPy, Pandas, SciPy. These are what you’ll be using initially. You can master the other libraries as you go. The basic idea is just to get acquainted to it. It’s going to be your best friend for a long long time. Once you’re comfortable with Python to a certain degree,

Now getting right to the action, Machine Learning | Eduonix Please do start this course right away. I’ll be brief about what the course covers and where it will leave you.

The course is an introductory course and will introduce to you the world of AI in the best possible manner. The course requires you to complete programming exercises on MATLAB/Octave as well so some hands-on practice straight away would do you good. MATLAB or Octave, the course guides you with the syntax all through until you develop familiarity with it. And needless to say, those languages are very easy to pick up too. So nothing to worry about for a beginner!

It should take you about a month (assuming you go reasonably fast) to get through the course.

Alright. So what’s the next stop? You’ve probably already heard about “Neural Networks” or “Deep Learning”. If not, some of these trending terms will come up in the course I mentioned prior and that’s the next stop on our roadmap here: Deep Learning!

There are a couple of ways to go about this. You can do a google search and take up any course that appeals to you but I took the subsequent specialisation (a set of courses on Coursera focused on a particular subject) by the same instructor, Andrew Ng, and was extremely happy with the content and more importantly, with how it opened my mind and added value to me. If I may, I’d direct you to the same course on our roadmap here: Deep Learning | Eduonix

This course covers various fronts of Deep Learning such as Hyperparameter Tuning (how to fine-tune your ANNs), Convolutional Neural Networks, Structuring AI Projects and a couple of other names that might sound a little daunting to you right now but I promise will only excite later on as you walk the road. It should take you about couple of months to get through the specialisation (assuming again, you go reasonably fast).

Now, this is a critical point in our path.

And there are folks all around. You could take on more courses and I wouldn’t have anything to argue against that. But have you not wondered to yourself by now, that it seems like the key to making a model give you good results depends in major part, to the data you feed the model. And data is the one thing you’ve been getting in your hands readymade all this time!

I hope the direction I’m pointing you towards is pretty clear. YES! Practice data acquisition and dataset cleaning! This is easily the most differential skill you can have that will most definitely get you a job! You can just go to Kaggle, enrol in a competition you find exciting and play around with the dataset. A very common statistic almost every other blog throws around is exactly this, “80% of the job in AI/ML/Data Science is dataset acquisition and cleaning”.

Well, now you’ve taken of things on that end too!

While you’re at it, also brush by data visualisation techniques which you can use to make your model’s results presentable and attractive. One thing I’ve always emphasised on is to develop a business perspective when it comes to AI. And for that, learning how to sell becomes integral.

You’ve come really far and I think it’s finally time you let your code talk.

Next stop: Projects.

You can do Projects from Youtube too

Credit card Fraud Detection Complete Project

This is where you will learn the maximum about the field and also about yourself and how you fit in. You can take up a project at any stage of your roadmap, of course. But the reason I won’t suggest that to you is that if you attempt a project without proper knowledge of the process, you will just end up copying things from somewhere to get the job done. This is the mistake many beginners and enthusiasts often make. They want to get the tag of “projects” under their name as quickly as possible just for the sake of their CV’s but don’t even know basic data acquisition of a website. Do not do that. Respect the process and the process will respect you back multifold.

We’ve finally reached the end of our little roadmap.

There are gates open for you all around now. Go grab apply for a job (which believe me, you will land easily) or learn other skills like Apache Spark, maybe learn a booming language like Scala or try your hands at functional programming or hell, go deeper into research and have some publications to yourself!

Everything is out there for you.

Everything.

And nobody, not even you can make yourself a roadmap for this juncture from now. Just trust yourself to figure it out when you do get here and back yourself on the fact that no matter where you go from now on, success will follow. Because you will give it no other choice