IB Computer Science HL · Year 2 · Lesson 50

Machine learning types, applications and hardware

Machine learning systems learn patterns from data; the learning approach, application and hardware shape what the system can do.

Paper 150 minutesA4.1.1 · A4.1.2
Use Next or the arrow keys.
Course homeIA hub2027 case study
Today’s targets

What you need to be able to do

2 / 8
  • DescribeThe types of machine learning and their applications in the real world
  • DescribeThe hardware requirements for various scenarios where machine learning is deployed
A4.1.1A4.1.2
Paper 1 lensMatch the depth of every response to the command term. Previously learned content can move quickly, but retrieval must still be accurate.
Page 2 of 8
Retrieve

Rapid Recall Deck

3 / 8

Say the answer aloud before flipping. Mark secure knowledge quickly and spend time on the gaps.

  • What is supervised learning?: Learning from labelled examples so a model can predict outputs for new inputs.
  • What is unsupervised learning?: Learning patterns or structure from data without labelled target outputs.
  • What is reinforcement learning?: An agent learns a policy through interaction with an environment and feedback in the form of rewards.
  • What is transfer learning?: Reusing knowledge learned by a model on one task or data set as a starting point for another related task.
  • What is deep learning?: Machine learning based on multi-layer neural networks that learn increasingly complex representations from data.
  • What advanced hardware and infrastructure can support ML workloads?: GPUs, TPUs, ASICs, FPGAs, edge devices, cloud platforms, and HPC centres.
  • Which hardware factors matter when choosing an ML deployment platform?: Processing requirements, storage capacity, memory/data movement, scalability, latency, power constraints, and the size/complexity of the workload.
  • What are some real-world applications of machine learning?: Market basket analysis, medical imaging diagnostics, natural language processing, object detection/classification, robotics navigation, and sentiment analysis.
Page 3 of 8
A4.1.1 + A4.1.2 · Learn

Core knowledge and application

4 / 8
A4.1.1Describe

The types of machine learning and their applications in the real world

Machine learning systems learn patterns from data; the learning approach, application and hardware shape what the system can do.

Exam moveGive a detailed, accurate account of what happens or what something is like.
Required detail 1The different approaches to machine learning algorithms and their unique characteristics
Required detail 2Deep learning (DL), reinforcement learning (RL), supervised learning, transfer learning (TL), unsupervised learning (UL)
Required detail 3Real-world applications of machine learning may include market basket analysis, medical imaging diagnostics, natural language processing, object detection and classification, robotics navigation, sentiment analysis

Explain it without notes

Describe: The types of machine learning and their applications in the real world in the context of a media company evaluating machine learning for image and text tasks.

  • The different approaches to machine learning algorithms and their unique characteristics
  • Deep learning (DL), reinforcement learning (RL), supervised learning, transfer learning (TL), unsupervised learning (UL)
  • Real-world applications of machine learning may include market basket analysis, medical imaging diagnostics, natural language processing, object detection and classification, robotics navigation, sentiment analysis
A4.1.2Describe

The hardware requirements for various scenarios where machine learning is deployed

Machine learning systems learn patterns from data; the learning approach, application and hardware shape what the system can do.

Exam moveGive a detailed, accurate account of what happens or what something is like.
Required detail 1The hardware configurations for different machine learning scenarios, considering factors such as processing, storage and scalability
Required detail 2Hardware configurations for machine learning ranging from standard laptops to advanced infrastructure
Required detail 3Advanced infrastructure must include application-specific integrated circuits (ASICs), edge devices, field-programmable gate arrays (FPGAs), GPUs, tensor processing units (TPUs), cloud-based platforms, high-performance computing (HPC) centres

Explain it without notes

Describe: The hardware requirements for various scenarios where machine learning is deployed in the context of a media company evaluating machine learning for image and text tasks.

  • The hardware configurations for different machine learning scenarios, considering factors such as processing, storage and scalability
  • Hardware configurations for machine learning ranging from standard laptops to advanced infrastructure
  • Advanced infrastructure must include application-specific integrated circuits (ASICs), edge devices, field-programmable gate arrays (FPGAs), GPUs, tensor processing units (TPUs), cloud-based platforms, high-performance computing (HPC) centres
Page 4 of 8
Apply

Transfer to a new scenario

5 / 8
ScenarioA media company evaluating machine learning for image and text tasks needs a design or technical decision related to today’s topic. Explain what matters and why.
  • The different approaches to machine learning algorithms and their unique characteristics
  • Deep learning (DL), reinforcement learning (RL), supervised learning, transfer learning (TL), unsupervised learning (UL)
  • The hardware configurations for different machine learning scenarios, considering factors such as processing, storage and scalability
  • Hardware configurations for machine learning ranging from standard laptops to advanced infrastructure
Page 5 of 8
Exam lens

Paper 1 practice

6 / 8
Build the response before checking notesUse precise terminology and match the required depth.
  1. Describe: The types of machine learning and their applications in the real world in the context of a media company evaluating machine learning for image and text tasks.
  2. Describe: The hardware requirements for various scenarios where machine learning is deployed in the context of a media company evaluating machine learning for image and text tasks.
Self-checkAnswer the exact command term. For explain, include mechanism/reason; for compare, pair criteria; for discuss/evaluate/justify, build supported reasoning and a conclusion.
Page 6 of 8
2027 Case Study

Generative AI research checkpoint

7 / 8

Build a reusable evidence bank for Paper 1 Section B. Keep claims technical, specific and supported.

Bias mitigationActions taken to reduce systematic unfairness in data, training or model outputs.
Know and apply in case-study context
Diffusion modelA generative model that produces data by iteratively reversing a noise process.
Know and apply in case-study context
Noise injectionAdding random noise to data; in diffusion systems this is part of the forward process used during training.
Know and apply in case-study context
Generative adversarial network (GAN)A generative system in which a generator produces candidates and a discriminator learns to distinguish generated data from real data.
Deep for HL where tied to GAN/hybrid challenges
Latent spaceA compressed numerical representation in which learned features are encoded.
Broad understanding sufficient
Page 7 of 8
Homework

Finish the learning cycle

8 / 8

Exam preparation — main task

Complete targeted 2027 case-study research and cumulative Paper 1/Paper 2 practice. Record evidence and technical vocabulary you can use in extended responses.

Retrieval

Repeat today’s recall deck and revisit any item marked ‘Review again’.

Designed by David Xu
© 2026 David Xu. All rights reserved.
Educators and students are welcome to use these materials for non-commercial teaching and learning with attribution. Please share the original link when possible. Reposting, redistributing modified copies, removing attribution, or commercial use requires prior permission.
End of Lesson 50.