₹0 for students · Certificate · Beginner to intermediate

Machine Learning for Beginners

27 lessons of classic machine learning with Python and scikit-learn

Start free in the app

27 lessons · ~20 hours · 30-question final exam · pass mark 70%

About the course

What you’ll learn

Hands-on classic machine learning with real datasets from around the world: regression on pumpkin prices, classifying cuisines, clustering Nigerian music, NLP on hotel reviews, forecasting energy demand, reinforcement learning, putting a model in a web app, and debugging models responsibly. Each lesson has a study guide, the full lesson with notebooks and assignments, and a quiz. Pass every quiz and the final exam to earn a verifiable certificate.

scikit-learnRegressionClassificationClusteringNLPTime seriesReinforcement learningFlaskONNXResponsible AI

Part of the career track: 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

27 lessons in 9 parts

Introduction to machine learning

1
Introduction to Machine Learning
35 min · ML learns patterns from data instead of hand-written rules.
2
The History of Machine Learning
30 min · 1950: Turing's question and test; 1956: Dartmouth workshop names AI.
3
Building Fair ML Solutions with Responsible AI
35 min · Responsible AI principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, accountability.
4
Techniques of Machine Learning
35 min · Frame the question: regression, classification or clustering; check ML is needed.

Regression

5
Getting Started with Python and Scikit-learn
45 min · Tools: Python, VS Code with Jupyter, notebooks, scikit-learn.
6
Preparing and Visualising Data for Regression
45 min · Frame the question: can we predict pumpkin prices?
7
Linear and Polynomial Regression
55 min · Linear regression minimises squared errors (least squares).
8
Logistic Regression to Predict Categories
55 min · Logistic regression predicts categories via a sigmoid probability and threshold.

Building a web app with your model

9
Build a Web App to Use an ML Model
50 min · Serve models so people can use them; Flask is a lightweight Python web framework.

Classification

10
Introduction to Classification
45 min · Classification assigns categories: binary or multiclass.
11
Cuisine Classifiers 1
50 min · Use cheat sheets to choose suitable classifiers.
12
Cuisine Classifiers 2
50 min · Compare several algorithms on the same data split.
13
Build a Cuisine Recommender Web App
50 min · ONNX is a portable format for running models across frameworks and runtimes.

Clustering

14
Introduction to Clustering
45 min · Clustering groups similar unlabelled items (unsupervised).
15
K-Means Clustering
50 min · K-means: assign points to nearest centroid, move centroids to means, repeat.

Natural language processing

16
Introduction to Natural Language Processing
35 min · NLP lets computers understand, generate and translate human language.
17
Common NLP Tasks and Techniques
45 min · Tokenisation splits text into words or sentences.
18
Translation and Sentiment Analysis
40 min · Word-by-word translation fails; grammar, order and idiom differ between languages.
19
Sentiment Analysis with Hotel Reviews: Exploring the Data
50 min · 515K Booking.com reviews with separate positive and negative texts, scores and tags.
20
Sentiment Analysis with Hotel Reviews: Analysis
50 min · Clean and group messy tags into useful guest-type features.

Time series forecasting

21
Introduction to Time Series Forecasting
40 min · A time series is observations ordered in time; forecasting predicts future values.
22
ARIMA Forecasting
55 min · ARIMA = autoregression (lags) + integration (differencing) + moving average (past errors).
23
Time Series Forecasting with Support Vector Regression
45 min · Turn forecasting into supervised learning with sliding windows of past values.

Reinforcement learning

24
Introduction to Reinforcement Learning and Q-Learning
55 min · RL: an agent acts in an environment, receiving states and rewards.
25
CartPole: Reinforcement Learning with Gym
50 min · Gym/Gymnasium environments share reset() and step(action).

Machine learning in the real world

26
Machine Learning in the Real World
35 min · Finance: fraud detection, risk and wealth management.
27
Debugging Models with the Responsible AI Dashboard
45 min · Overall metrics can hide failures for specific groups.

Course content is adapted from Microsoft's "Machine Learning for Beginners" curriculum (https://github.com/microsoft/ML-For-Beginners), used under the MIT License, Copyright (c) Microsoft Corporation. Study guides and quiz questions are written by Vikosha. Certificates are issued by Vikosha and are not issued or endorsed by Microsoft. Licence: MIT License, Copyright (c) Microsoft Corporation. View the original curriculum