When I decided that I wanted to seriously start learning Artificial Intelligence, I quickly realized that one of the hardest parts wasn't finding resources.
It was figuring out where to start.
There are countless courses, YouTube playlists, roadmaps, tools, frameworks, and technologies to learn. Every time I looked at what other people were doing, I felt like there was something else I should be learning.
So instead of trying to learn everything at once, I decided to create a roadmap for myself.
This isn't a roadmap written by an AI expert or someone who has already mastered everything.
It's simply the roadmap I'm following as a B.Tech Computer Science (Artificial Intelligence) student who is still learning.
And I'm sharing it publicly because I want to document what works, what doesn't, and how my understanding changes along the way.
Why I Decided to Learn AI Seriously
I'm studying Computer Science with Artificial Intelligence, so AI has naturally become one of the areas I want to explore deeply.
But for a long time, I didn't really know how to approach it.
I knew that AI was important. I knew that Machine Learning, Deep Learning, and other AI technologies were becoming increasingly relevant.
But knowing that something is important and actually learning it are two completely different things.
After spending a lot of my first and second year without doing as much as I wanted, I realized that I couldn't keep waiting for the "right time" to begin.
I had to start somewhere.
So I decided to stop worrying about learning everything at once and focus on building my foundation first.
Step 1: Strengthening My Programming Foundation
Before jumping deeply into Machine Learning, I want to become more comfortable with programming.
Python is one of the main languages I'm using for my AI journey because of how widely it is used in data science and Machine Learning.
Alongside Python, I'm also learning C++ for Data Structures and Algorithms and working with Java for my college studies.
My goal isn't to become an expert in multiple languages.
It's to understand programming concepts well enough that the language itself doesn't become a barrier when I'm trying to solve a problem.
Step 2: Learning the Mathematics Behind AI
This is one part of AI that I initially underestimated.
Machine Learning isn't just about calling a library and training a model.
There is mathematics behind many of the concepts.
So I'm working on strengthening areas such as:
- Linear Algebra
- Matrices and Determinants
- Probability
- Statistics
- Basic Calculus and mathematical concepts used in ML
I'm learning these alongside my regular studies instead of trying to finish all the mathematics first.
Step 3: Data Handling
Once the programming and mathematical foundations become stronger, I want to become comfortable working with data.
This includes learning tools such as:
- NumPy
- Pandas
- Data visualization
- Data cleaning
- Data preprocessing
I think this stage is especially important because real-world Machine Learning isn't just about training models.
A large part of the work is understanding and preparing the data.
Step 4: Machine Learning
This is where I want to start understanding how Machine Learning actually works.
Instead of only learning how to use ML libraries, I want to understand the concepts behind the algorithms.
Some of the areas I plan to cover include:
- Supervised Learning
- Unsupervised Learning
- Regression
- Classification
- Clustering
- Model evaluation
- Feature engineering
- Overfitting and underfitting
- Model optimization
My goal is to be able to look at a problem and understand why a particular Machine Learning approach might be useful, rather than simply following a tutorial.
Step 5: Deep Learning
After building a solid Machine Learning foundation, I want to move toward Deep Learning.
This is where topics such as neural networks, CNNs, and other deep learning architectures come into the picture.
I've already had some exposure to Deep Learning through projects, but I want to understand it more systematically rather than only using pre-trained models.
Step 6: Learning Through Projects
This is probably the most important part of my roadmap.
I don't want my learning journey to become:
Watch a course → make notes → watch another course → forget everything.
I want to build things.
Even if my first projects aren't perfect, I believe that actually trying to solve a problem teaches me things that watching tutorials cannot.
One of the projects I've worked on is an AI-based civic issue mapper, where AI can be used to classify civic problems from images and help map them.
Projects like this help me understand how different concepts come together—from data and models to backend development and real-world applications.
Step 7: Learning in Public
This is where this blog comes in.
Instead of keeping everything private until I feel "good enough," I want to document my progress while I'm learning.
I'll share:
- Things I'm learning
- Concepts I find difficult
- Projects I'm building
- Mistakes I make
- Resources that actually help me
- Lessons I learn along the way
I'm hoping that this will also keep me accountable.
When you know that you're documenting your journey, it becomes a little harder to keep saying, "I'll start tomorrow."
I'm Not Following a Perfect Roadmap
One thing I've already realized is that learning doesn't always happen in a straight line.
Sometimes I'll have to go back and revise something.
Sometimes I'll spend days understanding a concept that looked simple at first.
Sometimes I'll change the order in which I'm learning things.
And that's okay.
This roadmap is a guide, not a strict schedule.
I don't want to rush through topics just so I can say I've completed them.
I'd rather understand fewer concepts properly than collect dozens of certificates without actually knowing how to use what I learned.
What I Want to Achieve
I don't expect to become an AI expert overnight.
My current goal is much simpler.
I want to become technically stronger, build meaningful projects, understand the fundamentals properly, and gradually become ready for internships and future opportunities.
And most importantly, I want to look back after a year and know that I actually made progress.
What's Next?
This is just the beginning of my AI learning journey.
I'll probably make mistakes. I'll probably change this roadmap. I'll probably discover new areas that I want to explore.
But this time, I don't want to wait until I know everything before I begin.
I'm going to learn, build, share, and improve along the way.
And if you're also learning AI or Computer Science, maybe we can figure it out together.
This is my roadmap for now.
Let's see where it takes me.
Top comments (0)