Everything from the 3 lessons of this topic on a few pages: the key idea of each lesson, the diagram to remember, the points to learn and the traps examiners set. Read it, cover it, test yourself.
A graph is a set of nodes (vertices) joined by edges (arcs). Edges can carry weights (a cost such as distance or time) and can be directed or undirected. AI uses graphs to model states and the moves between them, then searches them. Dijkstra's algorithm always visits the unvisited node with the smallest distance from the start, so it finds the shortest path to every node. A* chooses the node with the smallest f = g + h, where g is the cost so far and h is a heuristic estimate of the cost still to go, so it usually reaches the goal after visiting far fewer nodes.
The syllabus does not ask you to write code for a graph or a search. It asks you to explain how graphs help AI and to trace Dijkstra and A* by hand, so practise clear, complete working tables.
The edge A to B is the most direct way to B, but it is not the shortest: 4 is beaten by A → C → B = 3. Always compare and update; never treat a distance as final until you visit that node.
Do not stop A* when the goal first appears in the open list. Stop when the goal is chosen (has the smallest f): a cheaper route to it may still be found before then.
Machine learning is a branch of AI in which a program improves its performance on a task by learning patterns from data, instead of following rules a programmer has written. In supervised learning the training data is labelled with the correct output, and the model learns to map inputs to outputs (classification or regression). In unsupervised learning the data is unlabelled and the model finds its own structure, such as clusters. In reinforcement learning an agent acts in an environment and learns by trial and error to maximise its reward. Regression predicts a continuous value by fitting a line or curve that minimises the error.
Unsupervised does not mean "no human involved". It means the training data has no labels, so the algorithm must find the groups itself; a human still chooses the data and interprets the clusters.
A regression model is only trustworthy inside the range of its training data. Predicting for 40 hours gives 211.7, an impossible score: extrapolating far beyond the data breaks the model.
"Supervised" refers to labelled training data, not to a person watching the program run. Justify your choice by describing the data.
An artificial neural network (ANN) is made of nodes (artificial neurons) arranged in an input layer, one or more hidden layers and an output layer. Each connection has a weight. A node calculates the weighted sum of its inputs plus a bias and passes it through an activation function. Deep learning uses ANNs with many hidden layers that learn features from raw data by themselves. The network is trained by back propagation of errors: compare the output with the target, pass the error backwards through the layers, and adjust every weight a little to reduce the error.
Do not forget the bias. It is added to the weighted sum before the activation function, and leaving it out changes the answer.
Deep learning is not a separate fourth category alongside supervised, unsupervised and reinforcement learning. It is a technique (deep neural networks) that can be used within any of them.
"The error is sent back and the weights are changed" is too vague for full marks. Say that the error is calculated at the output, propagated backwards layer by layer, and each weight is adjusted in proportion to its contribution to the error.