18.1 Artificial Intelligence (AI)

2026 Syllabus Objectives

By the end of this topic, you should be able to:

  • understand how graphs can be used to help Artificial Intelligence (AI)
  • understand the purpose and structure of a graph
  • use Dijkstra’s algorithm to search a graph
  • use the A* algorithm to search a graph
  • understand how artificial neural networks have helped machine learning
  • understand Machine Learning, Deep Learning, and Reinforcement Learning
  • explain the reasons for using these methods
  • understand the main machine learning categories, especially supervised learning and unsupervised learning
  • understand back propagation of errors
  • understand regression methods in machine learning

Main Content

https://cambridgeassistant.com

What is Artificial Intelligence?

Artificial Intelligence (AI) means making computers do tasks that normally need human intelligence. These tasks include learning from examples, spotting patterns, making decisions, and solving problems.

A simple way to think about AI is this: a normal program follows fixed instructions written by a human, but an AI system can often improve its behaviour by using data.

AI is a very broad field. Inside AI, there are smaller areas such as machine learning and deep learning. This means:

  • AI is the biggest area
  • Machine Learning is part of AI
  • Deep Learning is part of Machine Learning

So, deep learning is a special type of machine learning, and machine learning is a special type of AI.

AI is used in many real situations, such as route planning, smart assistants, search engines, face recognition, spam filtering, and translation systems.

How graphs are used to aid AI

A graph is a structure made of nodes and edges.

  • A node (also called a vertex) is a point in the graph.
  • An edge is a line joining two nodes.
  • An edge can have a weight, which is a number showing cost, distance, time, or some other value.

A graph is useful because it can represent a real problem in a simple form. For example:

  • nodes can represent towns, web pages, stations, rooms, or states in a problem
  • edges can represent roads, links, routes, or possible moves
  • weights can represent distance, time, travel cost, or risk

This is why graphs are helpful in AI. Many AI problems can be turned into a pathfinding problem, where the system must find the best path from one node to another.

For example, if a map is turned into a graph:

  • each town becomes a node
  • each road becomes an edge
  • each road distance becomes a weight

Then an AI system can search the graph to find the shortest route.

Graphs help AI because they:

  • show relationships clearly
  • make route-finding easier
  • allow the computer to compare different possible paths
  • can be searched using special algorithms such as Dijkstra’s and A*

Graphs are also important in machine learning because an artificial neural network can be pictured as a graph. In that graph, the nodes are artificial neurons and the edges are the weighted connections between them.

Sign in to view full notes