Machine Learning and Deep Learning
Machine learning (ML) is an umbrella term for different AI systems that can learn from past data to process new data and make predictions, classifications, and decisions.
Deep learning (DL) is a subset of ML that specifically deals with neural networks which are inspired by the structure of the human brain.
Some information about the learning material found on this page:
- the first three learnings on this page are suitable for all staff, and the latter learnings are suitable for Government Digital and Data professionals, or those with a technical interest
- there is no need to complete all learning material; choose what is relevant to you
- all learning material is free, but may require the creation of a free account to access
- some learning material contains practical exercises requiring a licence; exercises can be skipped if necessary
Learning Outcomes
Based on the learning material you choose, you will be able to:
- explain Machine Learning (ML), Deep Learning (DL), and neural networks
- describe the principles of fairness and bias when using ML and DL
- identify the process to build, train, and deploy ML models
- define decision forests, clustering, and recommendation systems
Learning Material
What is a neural network?
IBM article explaining neural networks and how they are associated with ML and DL.
Machine Learning Basics
Amazon Web Services (AWS) visual course introducing ML concepts by linking to real world examples.
Introduction to machine learning concepts
Microsoft written course introducing different types of ML and core concepts of DL.
Machine Learning & Deep Learning
IBM eLearning exploring multiple areas of AI, how they relate and impact society.
Machine Learning Terminology and Process
AWS visual course describing the ML process, terms used and steps involved in an ML project.
Introduction to machine learning operations (MLOps)
Microsoft written course introducing DevOps principles in relation to ML projects.
End-to-end machine learning operations (MLOps) with Azure Machine Learning
Microsoft written course applying DevOps principles to ML projects using GitHub actions.
Introduction to Machine Learning Problem Framing
Google written course examining if ML is the right approach to a problem, and how to outline an ML solution.
Decision Forests
Google written course exploring decision trees and forests, how they make predictions, and their limitations.
Introduction to Clustering
Google written course examining preparing data, defining similarity and evaluation of the quality of clustering results.
Introduction to Amazon SageMaker
AWS visual course introducing Amazon SageMaker to quickly build, train, and deploy machine learning models.
Amazon SageMaker JumpStart Foundations
AWS eLearning explaining Amazon SageMaker JumpStart, an ML hub with foundation models and prebuilt ML solutions.
Building Language Models on AWS
AWS eLearning exploring building small to large language models (LLMs), covering storage and ingestion options for processing large amounts of text.
Machine Learning Learning Plan
AWS curated learning path designed to help Data Scientists and Developers integrate ML and AI into tools and applications.
Introduction to AI and Machine Learning on Google Cloud
Coursera Visual learning introducing Google Cloud AI tools, including GenAI, and build end-to-end ML models using Vertex AI for projects.