Memory hook: Predict a label, predict a number, find a group, or generate content: these are different jobs.
Must remember
- AI is the broad field; machine learning learns patterns from data; deep learning uses multilayer neural networks. Generative AI creates content; agentic AI combines models with tools and control logic to pursue tasks. These categories overlap.
- Supervised learning uses labelled examples: classification predicts a category, regression a numeric value. Unsupervised learning finds structure without target labels, such as clustering. Reinforcement learning improves a policy through rewards from interaction; it is not simply a model with more labelled rows.
- Tabular and time-series data are different from unstructured text, image and audio. Preserve sequence in time-series validation; future information must not leak into training features. Labels must represent the real business outcome.
- Training changes model parameters; inference uses the resulting model. A deterministic tax rule is often better implemented as ordinary code than probabilistic prediction. Choose traditional ML when structured prediction or explainability fits; choose a foundation model when its general language, visual or other learned capabilities help.
- Speech to text: Transcribe. Text to speech: Polly. Language translation: Translate. Text entities/sentiment: Comprehend. Conversational interfaces: Lex. Document extraction: Textract. Image/video analysis: Rekognition. Custom model lifecycle: SageMaker AI. Managed foundation-model applications: Bedrock.
Choose under exam pressure
| Requirement | Choice and reason |
|---|---|
| Predict a house price | Regression. |
| Group similar customers without labels | Clustering. |
| An exact legal formula must always give the same answer | Deterministic application logic, with validation. |
Traps
- Classification confidence is not proof of truth.
- A large language model is not automatically better for a small tabular prediction.
- Selecting a managed service does not remove data-quality responsibility.
Active recall
1. Fraud or legitimate: which learning task?
Binary classification using suitable labelled examples.
2. Predict next month's demand: which output type?
A numeric forecast; time ordering affects evaluation.
3. What does clustering lack that supervised classification requires?
Known target labels for training examples.
4. A model recommends actions based on rewards. Which approach?
Reinforcement learning.
5. Which service turns a transcript into another language?
Translate. Transcribe would first convert speech into the transcript.