About this course
A structured, code-based progression through machine learning in Python. Delegates start with linear and logistic regression, then work through regularisation, support vector machines, decision trees, ensemble methods and unsupervised learning, before building deep learning models with neural networks. The course uses scikit-learn, pandas and Keras, and covers pipelines, cross-validation and model selection along the way.
Why this course
Teams that rely on point-and-click tools or outside contractors often cannot adapt models to their own data. Python is the main language for machine learning work, and staff who can code models end to end can build, test and maintain them in-house. This course builds that capability from first principles to deep learning.
What delegates will be able to do
By the end of the course, delegates will be able to
- Implement linear and logistic regression models in Python with scikit-learn
- Apply regularisation and cross-validation to select a well-generalising model
- Train and compare support vector machines, decision trees and ensemble models
- Build a reproducible machine learning pipeline from raw data to predictions
- Construct and train a simple deep learning model using Keras
Who should attend
Analysts, developers, statisticians and junior data scientists who can already write basic Python and want a thorough technical grounding in machine learning. Familiarity with algebra and introductory statistics is expected.
How it is delivered
Coding-intensive labs in Jupyter notebooks, with each topic introduced through a short explanation, a worked example and an exercise on a realistic dataset. It is available as a public course, in-house at your premises, or as live virtual sessions. Duration and dates are confirmed in your quote, and in-house groups can have the examples and exercises fitted to their organisation.