I taught myself machine learning more than 10 years ago.
If I had to start again today, I wouldn’t touch models, LLMs, or agents first, as many AI experts suggest.
I'd start with the math and the code.
Ugly truth: 90% of people skip the foundations, then wonder why everything feels like magic or falls apart in production.
If you want to be different, actually understand ML, not just copy-paste,
this is the roadmap I'd follow:
🚀 𝗦𝘁𝗮𝗿𝘁 𝘄𝗶𝘁𝗵 𝗳𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀
Because no matter how fast LLMs or GenAI evolve, your math, code, and logic will keep you relevant.
Here’s what you should focus on to learn ML in 2025.
Step-by-step roadmap:
1. Linear Algebra
Learn these core ideas:
Vectors, matrices, tensors
Matrix multiplication (dot products, broadcasting)
Transpose, inverse, rank, determinants
Eigenvalues & eigenvectors (especially for PCA & embeddings)
Projections and orthogonality
✅ Use NumPy to implement everything yourself
→ Practice matrix ops, dot products, and visualizing transformations with Matplotlib
2. Calculus
Focus on:
Derivatives & partial derivatives
Chain rule (for backpropagation in neural nets)
Gradient descent
Convex functions, minima/maxima
✅ Use SymPy or JAX to visualize and compute derivatives
→ Plot functions and their gradients to develop deep intuition
3. Probability
You need a solid grip on:
Random variables (discrete & continuous)
Conditional probability & Bayes' rule
Joint & marginal probability
The Chain rule
Expectation, variance, entropy
Common distributions: Bernoulli, Binomial, Gaussian, Poisson
Central limit theorem
The law of large numbers
✅ Simulate simple probability experiments in Python with NumPy
→ E.g. simulate sampling from distributions
4. Statistics
These are must-know topics:
Descriptive stats: mean, median, mode, standard deviation
Hypothesis testing: p-values, confidence intervals, t-tests
Correlation vs. causation
Sampling, bias, and variance
Overfitting/underfitting
A/B testing basics
✅ Use Pandas & SciPy to explore real datasets
→ Calculate descriptive stats, create histograms/box plots, run t-tests
5. Python and essential libraries
Python is the most popular programming language for ML.
If you already have experience in any programming language, you can learn Python in just a few days.
Next, focus on Python libraries for data manipulation and visualization.
🔧 Essential Python libraries you should learn early:
NumPy – for vectorized math and fast array ops
Pandas – for loading, cleaning, and analyzing tabular data
Matplotlib / Seaborn – for plotting and visualizing distributions, relationships, and trends
SymPy – for symbolic math and calculus
SciPy – for stats, optimization, and numerical methods
✅ Use Jupyter Notebooks(to combine math, code, & visuals in one place) and explore the capabilities of these libraries.
6. Key concepts of ML and ML frameworks
Discover how different ML algorithms work and when you should use each one of them (start with basics: linear regression, decision trees, random forest, support vector machines etc.)
Choose 1 algorithm and 1 framework and spend time coding, not just watching tutorials.
Don’t skip from one framework to another; stick with the one so you don’t lose precious time and energy.
Most used ML frameworks:
Scikit-learn:
beginner friendly
supports both unsupervised and supervised learning
effective for predictive data analysis and feature engineering
PyTorch:
beginner friendly
open-source
popular deep-learning framework
TensorFlow:
end-to-end ML platform that offers feature engineering and model serving
robust scalability that works across a wide range of data sets
7. Hands-on practice & build a small project
Choose a beginner ML course and put theory into practice by diving into real-world data sets on Kaggle and applying your new skills to a simple project using PyTorch or TensorFlow.
This way, you can create a portfolio that you can use when applying to the ML engineer role.
📚 Best resources to nail the fundamentals:
✅ Machine Learning Foundations Math series (ML Foundations: Linear Algebra, Calculus, Probability, and Statistics) a series of 4 courses that I've created together with LinkedIn learning
✅ Hands-On ML with TensorFlow & Keras book by Aurélien Géron
✅ The Hundred-page Machine Learning Book by Andriy Burkov
Thanks for the read!
Comment below and share the newsletter/ issue if you think it is relevant!
Feel free to also follow me on LinkedIn (very active), Instagram ( active), or X (not so active).
See you amazing folks next week!