₹0 for students · Certificate · Intermediate

Optimisation for Machine Learning

1 mini course, 5 lessons: objectives and constraints, linear programming, gradient methods, search heuristics and tuning models

Start free in the app

5 lessons · ~1 hours · 10-question final exam · pass mark 70%

About the course

What you’ll learn

Optimisation is how machine learning models learn and how businesses plan deliveries, schedules and budgets. Learn to state an optimisation problem, solve linear programs, understand gradient descent, momentum and Adam, handle constraints and hard combinatorial problems with smart heuristics, and tune ML models with loss functions, regularisation and hyperparameter search. Pass every lesson quiz and the final exam to earn a verifiable certificate.

OptimisationLinear programmingGradient descentMaths for ML

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: 10 questions in 20 minutes.
  4. Get a certificate with a public verification link, and add it to LinkedIn.

Syllabus

5 lessons in 1 mini courses

Each mini course takes about an hour. Already know one? Test out in the app and skip it.

1. Optimisation essentials

Formulate and solve optimisation problems and apply the methods that train ML models.

1
Stating an Optimisation Problem
10 min · Three parts: decision variables, objective, constraints.
2
Linear Programming
12 min · LPs have a linear objective and linear constraints.
3
Gradient Methods: SGD, Momentum and Adam
12 min · Gradient descent: w ← w − η∇L; SGD uses small random batches.
4
Constraints and Search Heuristics
12 min · Lagrange multipliers handle equality constraints; λ is a shadow price.
5
Optimisation Inside Machine Learning
12 min · Training = minimising a loss over the weights.

Written by Vikosha. Lessons, questions and exercises are original. Licence: Original Vikosha course..