₹0 for students · Certificate · Beginner to intermediate

Machine Learning Crash Course

16 lessons: the core ideas of machine learning, from regression to LLMs

Start free in the app

16 lessons · ~11 hours · 30-question final exam · pass mark 70%

About the course

What you’ll learn

A fast, rigorous introduction to how machine learning works: linear and logistic regression, loss and gradient descent, classification metrics, preparing numerical and categorical data, overfitting and regularisation, neural networks, embeddings, large language models, production systems, AutoML and fairness. Each lesson has a study guide, links to Google's interactive module and exercises, and a quiz. Pass every quiz and the final exam to earn a verifiable certificate.

Machine learningLinear regressionLogistic regressionGradient descentPrecision and recallFeature engineeringRegularisationNeural networksEmbeddingsML fairness

Part of the career tracks: Data Analyst, Machine Learning Engineer

How the certificate works

  1. Read each lesson’s study guide, then the full lesson and any notebooks or exercises.
  2. Pass every lesson quiz with 70% or more.
  3. Pass the final exam: 30 questions in 45 minutes.
  4. Get a certificate with a public verification link, and add it to LinkedIn.

Syllabus

16 lessons in 4 parts

ML models

1
Linear Regression and Loss
45 min · Supervised learning learns from features and labels; regression predicts numbers.
2
Gradient Descent and Hyperparameters
45 min · Gradient descent repeatedly steps parameters opposite to the loss gradient.
3
Logistic Regression
40 min · Logistic regression outputs probabilities between 0 and 1.
4
Classification: Thresholds and the Confusion Matrix
40 min · Classification assigns categories; a threshold turns probabilities into decisions.
5
Classification Metrics: Precision, Recall, ROC and AUC
45 min · Accuracy can mislead with imbalanced classes.

Data

6
Working with Numerical Data
45 min · Visualise and check features before training; models see feature vectors.
7
Working with Categorical Data
40 min · Encode categories without implying a false order.
8
Datasets, Splits and Generalisation
40 min · Generalisation: performing well on new, unseen data.
9
Overfitting and Regularisation
40 min · Overfitting: great on training data, poor on new data; underfitting: too simple.

Advanced ML models

10
Neural Networks
55 min · Neural networks learn non-linear patterns without hand-made feature crosses.
11
Embeddings
45 min · Embeddings map categories to short dense vectors.
12
Introduction to Large Language Models
50 min · Language models predict the next token; tokens are words or word pieces.

Real-world ML

13
Production ML Systems
45 min · The model is a small part; data, features, serving and monitoring dominate.
14
AutoML
30 min · AutoML automates feature work, algorithm choice and hyperparameter tuning.
15
ML Fairness
45 min · Models can absorb and amplify human and historical biases.
16
Putting It Together: An ML Project Checklist
30 min · Frame the problem and decide whether ML is needed.

This course is based on Google's Machine Learning Crash Course (https://developers.google.com/machine-learning/crash-course), whose text is licensed under CC BY 4.0 and code samples under Apache 2.0. Vikosha wrote new study guides and quiz questions; changes were made. Certificates are issued by Vikosha and are not issued or endorsed by Google. Licence: Text CC BY 4.0, code samples Apache 2.0, by Google. View the original curriculum