Python & Maths for Machine Learning

The working toolkit behind every model: NumPy, pandas, and the linear algebra, calculus and probability you actually use in machine learning — taught through code.

⏰ 8 weeks🎯 Standard🧩 Certificate🖥 Any device · our GPUs

Apply for this course Where this leads

Generated from this course

🎯 About this course

Most people who struggle with machine learning are not stuck on the models — they are stuck on the foundations: shapes, gradients, probability and vectorised thinking. This course fixes that, quickly and practically.

Each session pairs one idea with a graded coding lab: NumPy and pandas, linear algebra, calculus and gradient checks, probability and the bootstrap, vectorisation, and gradient descent from scratch. The course ends with MiniML, a small scikit-learn-style library you write and test yourself.

Who it is for

Career switchers, new graduates and working developers who want the mathematical footing to understand — not just call — machine-learning libraries.

What you will be able to do

Read an ML paper's notation without panic, debug shapes and gradients, and explain the uncertainty behind a metric.

By the end you will be able to

Use NumPy and pandas to load, clean, transform and summarise tabular data using vectorised operations.
Apply vectors, matrices, projections and least squares to model and solve ML problems.
Compute and verify gradients using the chain rule and numerical gradient checks.
Reason about uncertainty using Bayes' rule and bootstrap confidence intervals.
Implement linear and logistic regression with gradient descent and diagnose learning-rate and scaling problems.
Build a tested, leakage-free machine-learning pipeline with a scikit-learn-style API.

Curriculum

Topics covered

Core topics 6 topics

Python for data — NumPy, pandas, plotting
Comfort with NumPy arrays — vectorised operations, broadcasting, shapes — and pandas DataFrames — selecting, filtering, grouping, merging — is the baseline for every…
Linear algebra that matters for ML
You need working fluency with vectors, matrices, dot products, matrix multiplication shapes, and what a matrix transform does geometrically — not proofs, but enough…
Calculus, gradients and optimisation
A gradient tells you the direction of steepest increase of a function; gradient descent moves parameters in the opposite direction to reduce a loss function — this…
Probability and statistics
Core ideas you'll use constantly: probability distributions, expectation and variance, conditional probability and Bayes' rule, and what a p-value or confidence interval…
Vectorised thinking and performance
Replacing explicit Python loops with array/tensor operations (vectorisation) is usually 10-100x faster because the loop runs in optimised C/CUDA code instead of the…
From maths to code: gradient descent from scratch
Implementing gradient descent for a simple linear model by hand — compute predictions, compute loss, compute the gradient, update the weights, repeat — makes the…

Course at a glance

See how this course is built

Where the time goes

Longer spokes mean more hours on that module.

Course roadmap click a step

Try a lesson0 / 3

Sample questions from this course. Your progress is kept only in your browser.

Week by week

Drag the slider, or press play, to walk through the course and see what you will have built by each week.

Week 1 of 8

Wk 1–2

Python and the data stack

You produceA cleaned dataset and an exploratory analysis notebook

Wk 3–5

Linear algebra and calculus, in code

You produceGradient descent implemented from scratch on a real dataset

Wk 6–8

Probability, statistics and a mini-project

You produceA documented analysis with uncertainty quantified — the certificate lab

What you'll build

NumPy data helpers with tests

Vectorised standardisation, moving averages and group statistics with automatic tests.

A reusable gradient checker

A tested numerical-gradient utility that flags incorrect analytic gradients.

MiniML — a tested ML library

A small scikit-learn-style library with split, scaler, linear and logistic regression, metrics and bootstrap intervals, plus tests and a README.

Why take this course

Maths taught through code you run — no proof-writing
Auto-graded labs so you always know where you stand
Builds the intuition that makes every later ML course easier
Runs on any laptop — NumPy and pandas only

You will build

NumPy helpers for standardising, windowing and grouping data
A gradient checker that finds bugs in any model
Linear and logistic regression trained by gradient descent from scratch
MiniML: a small tested library with a scikit-learn-style API

What you can do afterwards

Read and write the vectorised code ML libraries are built from
Verify gradients and diagnose training problems
Report model metrics with honest confidence intervals

Career fit

🧭 Where this fits

Roles whose screened skills map to this course, and the skills it lets you show.

Skills you will build

Linear algebra & calculus for ML
Probability & statistics for ML
Python, NumPy / pandas, the ML maths

How to take it

💳 Delivery & fees

One course, four ways to attend. Fees are per course, in rupees excluding 18% GST (the GST-inclusive amount is shown too) with Canadian-dollar fees alongside.

Your fee includes our GPU lab infrastructure — no cloud credits to buy. See how we compare, with sources →