FeedbackShare feedback

← All sections·Learning path

IX

Specialized Domains14

Advanced

AI applied to medicine, science, audio, and other fields where domain knowledge changes everything.

Active Learning

A machine learning paradigm where the model identifies which unlabelled examples would be most valuable to label next - reducing the amount of human annotation needed by focusing labelling effort on the most informative data points.

AI for Science

The application of machine learning to accelerate scientific discovery - from predicting protein structures to simulating quantum systems to discovering new materials - transforming centuries-old scientific processes with data-driven pattern recognition.

Anomaly Detection

The task of identifying rare events or observations that deviate significantly from expected patterns - used to catch fraud, detect system failures, find manufacturing defects, and flag medical abnormalities.

All concepts

A

C

Code Generation
AI systems that write, complete, explain, debug, and translate code across programming languages - transforming software development by making code synthesis from natural language descriptions or context possible at production quality.

D

Differential Privacy
A rigorous mathematical framework for measuring and bounding the privacy risk of statistical analyses and machine learning - providing a quantifiable guarantee that individual records cannot be inferred from model outputs or aggregate statistics.

E

Edge AI
Running AI inference directly on edge devices - smartphones, IoT sensors, cameras, and embedded systems - rather than in the cloud, enabling real-time responsiveness, offline capability, and privacy by keeping data local.

F

Federated Learning
A machine learning approach that trains models across many distributed devices or data silos without centralising the raw data - each participant trains on their local data and shares only model updates, preserving privacy while enabling collective learning.

M

R

Recommendation System
The algorithms that decide what content, products, or connections to surface to each user - personalising feeds, search results, and product listings based on inferred individual preferences, past behaviour, and the behaviour of similar users.

S

Synthetic Data
Artificially generated data that mimics the statistical properties of real data - used to augment scarce training sets, preserve privacy, simulate rare events, and train AI systems when real-world data collection is impossible or prohibited.

T

Time Series Forecasting
The task of predicting future values of a sequence by learning patterns in historical data - applied everywhere from weather prediction to stock prices to energy demand to server load forecasting.