9618 · 18.1
Common exam mistakes on 9618 Artificial Intelligence (AI). Learn what loses marks, then practise the topic with Examiner’s Ink.
For your exam, you must be able to clearly distinguish between expert systems and machine learning. The key difference is the source of the 'knowledge': expert systems use explicitly programmed rules from humans, while machine learning models derive their own rules or patterns from data.
An expert system operates on a set of explicit, human-programmed IF-THEN rules stored in a knowledge base. A machine learning model is not explicitly programmed with rules; instead, it learns its own internal rules and patterns by processing large amounts of data.
No. Machine Learning is a specific approach to achieving AI. AI is the broader, overall concept of creating machines that can simulate human intelligence. ML is a subset of AI, and Deep Learning is a further subset of ML.
No, you are not required to write code for a neural network. You need to understand the conceptual model: the layered structure (input, hidden, output), the role of neurons and weights, the concept of training by adjusting weights, and its applications.
The key difference is the data used for training. Supervised learning uses a labelled dataset, where the correct answer or output is provided for every input example. Unsupervised learning uses an unlabelled dataset, and the algorithm must find patterns or groupings within the data on its own.