-
Intelligent Systems
In order to create intelligent systems we first need to define intelligence and understand the process of learning. Intelligence provides the foundation for acquiring, understanding, and applying knowledge, while learning represents the mechanism through which systems adapt and evolve. Together, these elements form the basis of intelligent systems, and intelligent behaviour.
-
Intelligence
Intelligence refers to the ability to acquire, understand, and apply knowledge and skills. It encompasses a range of cognitive functions, including reasoning, problem-solving, learning, perception, and decision-making. Intelligence can manifest in various forms, such as emotional intelligence, social intelligence, and logical-mathematical intelligence.
-
Learning
Learning is the process through which a system—human, animal, or artificial—acquires knowledge or skills through experience, instruction, or observation, and modifies its behaviour or internal representations accordingly.
-
-
Artificial Intelligence
Artificial Intelligence (AI) is a branch of computer science focused on creating systems capable of performing tasks that typically require human intelligence. These tasks include learning, reasoning, problem-solving, understanding natural language, and recognising patterns. AI systems can be categorised into narrow AI (designed for specific tasks) and general AI (aiming to perform any intellectual task a human can do).
-
Symbolic Artificial Intelligence
Symbolic Artificial Intelligence, also known as rule-based AI or classical AI, is an approach to AI that relies on explicitly programmed rules and symbolic representations of knowledge. It uses logic and reasoning to solve problems and make decisions. Symbolic AI was one of the earliest approaches to AI and is often contrasted with machine learning-based approaches, which rely on data and statistical methods. Unlike machine learning systems, symbolic AI does not learn from data but operates based on predefined rules and logic. Given that, some may say these are not truly intelligent systems.
-
Machine Learning
Machine Learning (ML) is a subset of artificial intelligence that focuses on developing algorithms and statistical models that enable computers to learn and make decisions without being explicitly programmed. ML systems typically improve their performance over time by analysing and learning from data, although performance can deteriorate if the data is biased, insufficient, or poorly representative.
-
Deep Learning
Deep Learning is a specialised subset of machine learning that uses artificial neural networks with multiple layers (hence "deep") to model and understand complex patterns in data. It is particularly effective for tasks such as image and speech recognition, natural language processing, and autonomous systems.
-
-
-
Learning Types
-
Supervised Learning
A machine learning approach where models are trained on labelled data, meaning each input is paired with a known output. The system learns to map inputs to outputs by minimising prediction errors. Common tasks include classification and regression.
-
Unsupervised Learning
A learning paradigm where models explore unlabelled data to uncover hidden patterns, structures, or groupings. It’s used for tasks like clustering, dimensionality reduction, and anomaly detection, without predefined outcomes.
-
Transfer Learning
A technique where knowledge gained from solving one task is reused to improve performance on a related task. Often involves adapting a pre-trained model to a new domain with limited data, reducing training time and improving generalisation.
-
Reinforcement Learning
A learning framework where an agent interacts with an environment, making decisions to maximise cumulative rewards over time. The agent learns through trial and error, balancing exploration of new actions with exploitation of known strategies. Widely used in robotics, game playing, and autonomous systems.
-