What is Machine Learning?
A way for computers to learn from examples instead of being given exact rules — by finding patterns in labelled or unlabelled data.
Machine Learning explained in plain English
Analogy
Machine learning is like learning to identify birds by looking at thousands of photographs with names attached, rather than memorising a field guide written by an expert. Eventually you start recognising patterns — shape, colour, size — without anyone spelling out every rule.
Example
Credit scoring, product recommendations, and medical risk prediction are everyday applications built on machine learning.
How is Machine Learning used?
Common misconceptions about Machine Learning
People also read
- Artificial Intelligence
Any system that performs tasks requiring human judgment — understanding language, recognising images, making decisions, or solving problems — by finding patterns in data rather than thinking or feeling.
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- Classification
The task of sorting inputs into predefined categories — choosing a label rather than producing a number.
- Embedding
A numerical representation of text, images, or other data that captures semantic meaning.
- Fine-tuning
The process of further training a pre-trained AI model on specialised data to improve performance on specific tasks.
- Gradient Descent
The method by which a model gradually improves by making small adjustments after each mistake, moving toward better performance.
- Inference
The phase when a trained model is actually used — taking new input and producing a prediction or response.
- Neural Network
A layered system that processes information in stages, with each layer detecting slightly more complex patterns than the last.
- Overfitting
When a model memorises training examples too precisely and fails to generalise to new data.
- Supervised Learning
Training a system using examples where the correct answer is already known, so it learns to map inputs to labels.