Interviews Vector
Back to Roadmap
2
18 lessons

ML Fundamentals

Classical ML — still the backbone of most production AI.

01

What Is Machine Learning

Learn
Python

Machine learning is teaching computers to find patterns in data instead of writing rules by hand.

02

Linear Regression from Scratch

Build
Python

Linear regression draws the best straight line through your data. It is the "hello world" of machine learning.

03

Logistic Regression & Classification

Build
Python

Logistic regression bends a straight line into an S-curve to answer yes-or-no questions with probabilities.

04

Decision Trees & Random Forests

Build
Python

A decision tree is just a flowchart. But a forest of them is one of the most powerful tools in ML.

05

Support Vector Machines

Build
Python

Find the widest street between two classes. That is the entire idea.

06

KNN & Distance Metrics

Build
Python

Store everything. Predict by looking at your neighbors. The simplest algorithm that actually works.

07

Unsupervised Learning: K-Means, DBSCAN

Build
Python

No labels, no teacher. The algorithm finds structure on its own.

08

Feature Engineering & Selection

Build
Python

A good feature is worth a thousand data points.

09

Model Evaluation: Metrics, Cross-Validation

Build
Python

A model is only as good as the way you measure it.

10

Bias, Variance & the Learning Curve

Learn
Python

Every model error comes from one of three sources: bias, variance, or noise. You can only control the first two.

11

Ensemble Methods: Boosting, Bagging, Stacking

Build
Python

A group of weak learners, combined correctly, becomes a strong learner. This is not a metaphor. It is a theorem.

12

Hyperparameter Tuning

Build
Python

Hyperparameters are the knobs you turn before training starts. Turning them well is the difference between a mediocre model and a great one.

13

ML Pipelines & Experiment Tracking

Build
Python

A model is not a product. A pipeline is. The pipeline is everything from raw data to deployed prediction, and every step must be reproducible.

14

Naive Bayes

Build
Python

The "naive" assumption is wrong, and it works anyway. That's the beauty of it.

15

Time Series Fundamentals

Build
Python

Past performance does predict future results -- if you check for stationarity first.

16

Anomaly Detection

Build
Python

Normal is easy to define. Abnormal is whatever doesn't fit.

17

Handling Imbalanced Data

Build
Python

When 99% of your data is "normal," accuracy is a lie.

18

Feature Selection

Build
Python

More features is not better. The right features is better.